| 5 431 432 432 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases. * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value * * Return: microseconds value */ unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /** * mktime64 - Converts date to seconds. * @year0: year to convert * @mon0: month to convert * @day: day to convert * @hour: hour to convert * @min: minute to convert * @sec: second to convert * * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. * * Return: seconds since the epoch time for the given input date */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC. * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Return: the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h * * Return: jiffies value */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); /** * __usecs_to_jiffies: - convert microseconds to jiffies * @u: time in milliseconds * * Return: jiffies value */ unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /** * timespec64_to_jiffies - convert a timespec64 value to jiffies * @value: pointer to &struct timespec64 * * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundaries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. * * Return: jiffies value */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); /** * jiffies_to_timespec64 - convert jiffies value to &struct timespec64 * @jiffies: jiffies value * @value: pointer to &struct timespec64 */ void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ /** * jiffies_to_clock_t - Convert jiffies to clock_t * @x: jiffies value * * Return: jiffies converted to clock_t (CLOCKS_PER_SEC) */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); /** * clock_t_to_jiffies - Convert clock_t to jiffies * @x: clock_t value * * Return: clock_t value converted to jiffies */ unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); /** * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t * @x: jiffies_64 value * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); /** * nsec_to_clock_t - Convert nsec value to clock_t * @x: nsec value * * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } /** * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds * @j: jiffies64 value * * Return: nanoseconds value */ u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); /** * jiffies64_to_msecs - Convert jiffies64 to milliseconds * @j: jiffies64 value * * Return: milliseconds value */ u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies64 value */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies value */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /** * timespec64_add_safe - Add two timespec64 values and do a safety check * for overflow. * @lhs: first (left) timespec64 to add * @rhs: second (right) timespec64 to add * * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. * * Return: sum of @lhs + @rhs */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } /** * get_timespec64 - get user's time value into kernel space * @ts: destination &struct timespec64 * @uts: user's time value as &struct __kernel_timespec * * Handles compat or 32-bit modes. * * Return: 0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); /** * put_timespec64 - convert timespec64 value to __kernel_timespec format and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * * Return: 0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } /** * get_old_timespec32 - get user's old-format time value into kernel space * @ts: destination &struct timespec64 * @uts: user's old-format time value (&struct old_timespec32) * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); /** * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct old_timespec32 * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); /** * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); /** * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format * and copy the latter to userspace * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); /** * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); /** * put_old_itimerspec32 - convert &struct itimerspec64 to &struct * old_itimerspec32 and copy the latter to userspace * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 25 25 25 25 4 25 25 25 25 25 25 25 25 25 25 25 2 25 25 25 2 25 25 25 25 25 25 25 4 4 4 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 4 25 25 25 25 25 4 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/printk.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Modified to make sys_syslog() more flexible: added commands to * return the last 4k of kernel messages, regardless of whether * they've been read or not. Added option to suppress kernel printk's * to the console. Added hook for sending the console messages * elsewhere, in preparation for a serial line console (someday). * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/syscore_ops.h> #include <linux/vmcore_info.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> #include <asm/sections.h> #include <trace/events/initcall.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); EXPORT_TRACEPOINT_SYMBOL_GPL(console); /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. */ int oops_in_progress; EXPORT_SYMBOL(oops_in_progress); /* * console_mutex protects console_list updates and console->flags updates. * The flags are synchronized only for consoles that are registered, i.e. * accessible via the console list. */ static DEFINE_MUTEX(console_mutex); /* * console_sem protects updates to console->seq * and also provides serialization for console printing. */ static DEFINE_SEMAPHORE(console_sem, 1); HLIST_HEAD(console_list); EXPORT_SYMBOL_GPL(console_list); DEFINE_STATIC_SRCU(console_srcu); /* * System may need to suppress printk message under certain * circumstances, like after kernel panic happens. */ int __read_mostly suppress_printk; #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; void lockdep_assert_console_list_lock_held(void) { lockdep_assert_held(&console_mutex); } EXPORT_SYMBOL(lockdep_assert_console_list_lock_held); #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC bool console_srcu_read_lock_is_held(void) { return srcu_read_lock_held(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock_is_held); #endif enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, __DEVKMSG_LOG_BIT_LOCK, }; enum devkmsg_log_masks { DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), }; /* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ #define DEVKMSG_LOG_MASK_DEFAULT 0 static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; static int __control_devkmsg(char *str) { size_t len; if (!str) return -EINVAL; len = str_has_prefix(str, "on"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_ON; return len; } len = str_has_prefix(str, "off"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_OFF; return len; } len = str_has_prefix(str, "ratelimit"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; return len; } return -EINVAL; } static int __init control_devkmsg(char *str) { if (__control_devkmsg(str) < 0) { pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; } /* * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) strscpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) strscpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* * Sysctl cannot change it anymore. The kernel command line setting of * this parameter is to force the setting to be permanent throughout the * runtime of the system. This is a precation measure against userspace * trying to be a smarta** and attempting to change it up on us. */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; return 1; } __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; unsigned int old; int err; if (write) { if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) return -EINVAL; old = devkmsg_log; strscpy(old_str, devkmsg_log_str); } err = proc_dostring(table, write, buffer, lenp, ppos); if (err) return err; if (write) { err = __control_devkmsg(devkmsg_log_str); /* * Do not accept an unknown string OR a known string with * trailing crap... */ if (err < 0 || (err + 1 != *lenp)) { /* ... and restore old setting. */ devkmsg_log = old; strscpy(devkmsg_log_str, old_str); return -EINVAL; } } return 0; } #endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /** * console_list_lock - Lock the console list * * For console list or console->flags updates */ void console_list_lock(void) { /* * In unregister_console() and console_force_preferred_locked(), * synchronize_srcu() is called with the console_list_lock held. * Therefore it is not allowed that the console_list_lock is taken * with the srcu_lock held. * * Detecting if this context is really in the read-side critical * section is only possible if the appropriate debug options are * enabled. */ WARN_ON_ONCE(debug_lockdep_rcu_enabled() && srcu_read_lock_held(&console_srcu)); mutex_lock(&console_mutex); } EXPORT_SYMBOL(console_list_lock); /** * console_list_unlock - Unlock the console list * * Counterpart to console_list_lock() */ void console_list_unlock(void) { mutex_unlock(&console_mutex); } EXPORT_SYMBOL(console_list_unlock); /** * console_srcu_read_lock - Register a new reader for the * SRCU-protected console list * * Use for_each_console_srcu() to iterate the console list * * Context: Any context. * Return: A cookie to pass to console_srcu_read_unlock(). */ int console_srcu_read_lock(void) __acquires(&console_srcu) { return srcu_read_lock_nmisafe(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock); /** * console_srcu_read_unlock - Unregister an old reader from * the SRCU-protected console list * @cookie: cookie returned from console_srcu_read_lock() * * Counterpart to console_srcu_read_lock() */ void console_srcu_read_unlock(int cookie) __releases(&console_srcu) { srcu_read_unlock_nmisafe(&console_srcu, cookie); } EXPORT_SYMBOL(console_srcu_read_unlock); /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ #define down_console_sem() do { \ down(&console_sem);\ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ } while (0) static int __down_trylock_console_sem(unsigned long ip) { int lock_failed; unsigned long flags; /* * Here and in __up_console_sem() we need to be in safe mode, * because spindump/WARN/etc from under console ->lock will * deadlock in printk()->down_trylock_console_sem() otherwise. */ printk_safe_enter_irqsave(flags); lock_failed = down_trylock(&console_sem); printk_safe_exit_irqrestore(flags); if (lock_failed) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; } #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) static void __up_console_sem(unsigned long ip) { unsigned long flags; mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) static bool panic_in_progress(void) { return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } /* Return true if a panic is in progress on the current CPU. */ bool this_cpu_in_panic(void) { /* * We can use raw_smp_processor_id() here because it is impossible for * the task to be migrated to the panic_cpu, or away from it. If * panic_cpu has already been set, and we're not currently executing on * that CPU, then we never will be. */ return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); } /* * Return true if a panic is in progress on a remote CPU. * * On true, the local CPU should immediately release any printing resources * that may be needed by the panic CPU. */ bool other_cpu_in_panic(void) { return (panic_in_progress() && !this_cpu_in_panic()); } /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's * definitely not the perfect debug tool (we don't know if _WE_ * hold it and are racing, but it helps tracking those weird code * paths in the console code where we end up in places I want * locked without the console semaphore held). */ static int console_locked; /* * Array of consoles built from command line options (console=) */ #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; enum con_msg_format_flags { MSG_FORMAT_DEFAULT = 0, MSG_FORMAT_SYSLOG = (1 << 0), }; static int console_msg_format = MSG_FORMAT_DEFAULT; /* * The printk log buffer consists of a sequenced collection of records, each * containing variable length message text. Every record also contains its * own meta-data (@info). * * Every record meta-data carries the timestamp in microseconds, as well as * the standard userspace syslog level and syslog facility. The usual kernel * messages use LOG_KERN; userspace-injected messages always carry a matching * syslog facility, by default LOG_USER. The origin of every message can be * reliably determined that way. * * The human readable log message of a record is available in @text, the * length of the message text in @text_len. The stored message is not * terminated. * * Optionally, a record can carry a dictionary of properties (key/value * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * * Valid characters in property names are [a-zA-Z0-9.-_]. Property names * and values are terminated by a '\0' character. * * Example of record values: * record.text_buf = "it's a line" (unterminated) * record.info.seq = 56 * record.info.ts_nsec = 36863 * record.info.text_len = 11 * record.info.facility = 0 (LOG_KERN) * record.info.flags = 0 * record.info.level = 3 (LOG_ERR) * record.info.caller_id = 299 (task 299) * record.info.dev_info.subsystem = "pci" (terminated) * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) * * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" * * Users of the export format should ignore possible additional values * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. */ /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); /* * Specifies if a legacy console is registered. If legacy consoles are * present, it is necessary to perform the console lock/unlock dance * whenever console flushing should occur. */ bool have_legacy_console; /* * Specifies if an nbcon console is registered. If nbcon consoles are present, * synchronous printing of legacy consoles will not occur during panic until * the backtrace has been stored to the ringbuffer. */ bool have_nbcon_console; /* * Specifies if a boot console is registered. If boot consoles are present, * nbcon consoles cannot print simultaneously and must be synchronized by * the console lock. This is because boot consoles and nbcon consoles may * have mapped the same hardware. */ bool have_boot_console; /* See printk_legacy_allow_panic_sync() for details. */ bool legacy_allow_panic_sync; #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); static DECLARE_WAIT_QUEUE_HEAD(legacy_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; /* True when _all_ printer threads are available for printing. */ bool printk_kthreads_running; struct latched_seq { seqcount_latch_t latch; u64 val[2]; }; /* * The next printk record to read after the last 'clear' command. There are * two copies (updated with seqcount_latch) so that reads can locklessly * access a valid value. Writers are synchronized by @syslog_lock. */ static struct latched_seq clear_seq = { .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), .val[0] = 0, .val[1] = 0, }; #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* * Define the average message size. This only affects the number of * descriptors that will be available. Underestimating is better than * overestimating (too many available descriptors is better than not enough). */ #define PRB_AVGBITS 5 /* 32 character average length */ #if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS #error CONFIG_LOG_BUF_SHIFT value too small. #endif _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, PRB_AVGBITS, &__log_buf[0]); static struct printk_ringbuffer printk_rb_dynamic; struct printk_ringbuffer *prb = &printk_rb_static; /* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. */ static bool __printk_percpu_data_ready __ro_after_init; bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } /* Must be called under syslog_lock. */ static void latched_seq_write(struct latched_seq *ls, u64 val) { write_seqcount_latch_begin(&ls->latch); ls->val[0] = val; write_seqcount_latch(&ls->latch); ls->val[1] = val; write_seqcount_latch_end(&ls->latch); } /* Can be called from any context. */ static u64 latched_seq_read_nolock(struct latched_seq *ls) { unsigned int seq; unsigned int idx; u64 val; do { seq = read_seqcount_latch(&ls->latch); idx = seq & 0x1; val = ls->val[idx]; } while (read_seqcount_latch_retry(&ls->latch, seq)); return val; } /* Return log buffer address */ char *log_buf_addr_get(void) { return log_buf; } /* Return log buffer size */ u32 log_buf_len_get(void) { return log_buf_len; } /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available * when the index points to the middle. */ #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; if (*text_len > max_text_len) *text_len = max_text_len; /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); if (*text_len >= *trunc_msg_len) *text_len -= *trunc_msg_len; else *trunc_msg_len = 0; } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); static int syslog_action_restricted(int type) { if (dmesg_restrict) return 1; /* * Unless restricted, we allow "read all" and "get buffer size" * for everybody. */ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; } static int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; return -EPERM; } ok: return security_syslog(type); } static void append_char(char **pp, char *e, char c) { if (*pp < e) *(*pp)++ = c; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER u32 id = info->caller_id; snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); #else caller[0] = '\0'; #endif do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", (info->facility << 3) | info->level, info->seq, ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } static ssize_t msg_add_ext_text(char *buf, size_t size, const char *text, size_t text_len, unsigned char endc) { char *p = buf, *e = buf + size; size_t i; /* escape non-printable characters */ for (i = 0; i < text_len; i++) { unsigned char c = text[i]; if (c < ' ' || c >= 127 || c == '\\') p += scnprintf(p, e - p, "\\x%02x", c); else append_char(&p, e, c); } append_char(&p, e, endc); return p - buf; } static ssize_t msg_add_dict_text(char *buf, size_t size, const char *key, const char *val) { size_t val_len = strlen(val); ssize_t len; if (!val_len) return 0; len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); return len; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { ssize_t len; len = msg_add_ext_text(buf, size, text, text_len, '\n'); if (!dev_info) goto out; len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", dev_info->subsystem); len += msg_add_dict_text(buf + len, size - len, "DEVICE", dev_info->device); out: return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { atomic64_t seq; struct ratelimit_state rs; struct mutex lock; struct printk_buffers pbufs; }; static __printf(3, 4) __cold int devkmsg_emit(int facility, int level, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; } static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ struct file *file = iocb->ki_filp; struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; if (len > PRINTKRB_RECORD_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return len; /* Ratelimit when not explicitly enabled. */ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { if (!___ratelimit(&user->rs, current->comm)) return ret; } buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; buf[len] = '\0'; if (!copy_from_iter_full(buf, len, from)) { kfree(buf); return -EFAULT; } /* * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace * the decimal value represents 32bit, the lower 3 bit are the log * level, the rest are the log facility. * * If no prefix or no userspace facility is specified, we * enforce LOG_USER, to be able to reliably distinguish * kernel-generated messages from userspace-injected ones. */ line = buf; if (line[0] == '<') { char *endp = NULL; unsigned int u; u = simple_strtoul(line + 1, &endp, 10); if (endp && endp[0] == '>') { level = LOG_LEVEL(u); if (LOG_FACILITY(u) != 0) facility = LOG_FACILITY(u); endp++; line = endp; } } devkmsg_emit(facility, level, "%s", line); kfree(buf); return ret; } static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; char *outbuf = &user->pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &user->pbufs, }; ssize_t ret; ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; if (!printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; } /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ ret = wait_event_interruptible(log_wait, printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } if (pmsg.dropped) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, pmsg.seq); ret = -EPIPE; goto out; } atomic64_set(&user->seq, pmsg.seq + 1); if (pmsg.outbuf_len > count) { ret = -EINVAL; goto out; } if (copy_to_user(buf, outbuf, pmsg.outbuf_len)) { ret = -EFAULT; goto out; } ret = pmsg.outbuf_len; out: mutex_unlock(&user->lock); return ret; } /* * Be careful when modifying this function!!! * * Only few operations are supported because the device works only with the * entire variable length messages (records). Non-standard values are * returned in the other cases and has been this way for quite some time. * User space applications might depend on this behavior. */ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) { struct devkmsg_user *user = file->private_data; loff_t ret = 0; if (offset) return -ESPIPE; switch (whence) { case SEEK_SET: /* the first record */ atomic64_set(&user->seq, prb_first_valid_seq(prb)); break; case SEEK_DATA: /* * The first record after the last SYSLOG_ACTION_CLEAR, * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); break; case SEEK_END: /* after the last record */ atomic64_set(&user->seq, prb_next_seq(prb)); break; default: ret = -EINVAL; } return ret; } static __poll_t devkmsg_poll(struct file *file, poll_table *wait) { struct devkmsg_user *user = file->private_data; struct printk_info info; __poll_t ret = 0; poll_wait(file, &log_wait, wait); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } return ret; } static int devkmsg_open(struct inode *inode, struct file *file) { struct devkmsg_user *user; int err; if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return -EPERM; /* write-only does not need any file context */ if ((file->f_flags & O_ACCMODE) != O_WRONLY) { err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, SYSLOG_FROM_READER); if (err) return err; } user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); if (!user) return -ENOMEM; ratelimit_default_init(&user->rs); ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); mutex_init(&user->lock); atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; return 0; } static int devkmsg_release(struct inode *inode, struct file *file) { struct devkmsg_user *user = file->private_data; ratelimit_state_exit(&user->rs); mutex_destroy(&user->lock); kvfree(user); return 0; } const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, }; #ifdef CONFIG_VMCORE_INFO /* * This appends the listed symbols to /proc/vmcore * * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ void log_buf_vmcoreinfo_setup(void) { struct dev_printk_info *dev_info = NULL; VMCOREINFO_SYMBOL(prb); VMCOREINFO_SYMBOL(printk_rb_static); VMCOREINFO_SYMBOL(clear_seq); /* * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); VMCOREINFO_OFFSET(printk_ringbuffer, fail); VMCOREINFO_STRUCT_SIZE(prb_desc_ring); VMCOREINFO_OFFSET(prb_desc_ring, count_bits); VMCOREINFO_OFFSET(prb_desc_ring, descs); VMCOREINFO_OFFSET(prb_desc_ring, infos); VMCOREINFO_OFFSET(prb_desc_ring, head_id); VMCOREINFO_OFFSET(prb_desc_ring, tail_id); VMCOREINFO_STRUCT_SIZE(prb_desc); VMCOREINFO_OFFSET(prb_desc, state_var); VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); VMCOREINFO_OFFSET(prb_data_blk_lpos, next); VMCOREINFO_STRUCT_SIZE(printk_info); VMCOREINFO_OFFSET(printk_info, seq); VMCOREINFO_OFFSET(printk_info, ts_nsec); VMCOREINFO_OFFSET(printk_info, text_len); VMCOREINFO_OFFSET(printk_info, caller_id); VMCOREINFO_OFFSET(printk_info, dev_info); VMCOREINFO_STRUCT_SIZE(dev_printk_info); VMCOREINFO_OFFSET(dev_printk_info, subsystem); VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); VMCOREINFO_OFFSET(dev_printk_info, device); VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); VMCOREINFO_STRUCT_SIZE(prb_data_ring); VMCOREINFO_OFFSET(prb_data_ring, size_bits); VMCOREINFO_OFFSET(prb_data_ring, data); VMCOREINFO_OFFSET(prb_data_ring, head_lpos); VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); VMCOREINFO_STRUCT_SIZE(latched_seq); VMCOREINFO_OFFSET(latched_seq, val); } #endif /* requested log_buf_len from kernel cmdline */ static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ static void __init log_buf_len_update(u64 size) { if (size > (u64)LOG_BUF_LEN_MAX) { size = (u64)LOG_BUF_LEN_MAX; pr_err("log_buf over 2G is not supported.\n"); } if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { u64 size; if (!str) return -EINVAL; size = memparse(str, &str); log_buf_len_update(size); return 0; } early_param("log_buf_len", log_buf_len_setup); #ifdef CONFIG_SMP #define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) static void __init log_buf_add_cpu(void) { unsigned int cpu_extra; /* * archs should set up cpu_possible_bits properly with * set_cpu_possible() after setup_arch() but just in * case lets ensure this is valid. */ if (num_possible_cpus() == 1) return; cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; /* by default this will only continue through for large > 64 CPUs */ if (cpu_extra <= __LOG_BUF_LEN / 2) return; pr_info("log_buf_len individual max cpu contribution: %d bytes\n", __LOG_CPU_MAX_BUF_LEN); pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", cpu_extra); pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); log_buf_len_update(cpu_extra + __LOG_BUF_LEN); } #else /* !CONFIG_SMP */ static inline void log_buf_add_cpu(void) {} #endif /* CONFIG_SMP */ static void __init set_percpu_data_ready(void) { __printk_percpu_data_ready = true; } static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_reserved_entry e; struct printk_record dest_r; prb_rec_init_wr(&dest_r, r->info->text_len); if (!prb_reserve(&e, rb, &dest_r)) return 0; memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); dest_r.info->text_len = r->info->text_len; dest_r.info->facility = r->info->facility; dest_r.info->level = r->info->level; dest_r.info->flags = r->info->flags; dest_r.info->ts_nsec = r->info->ts_nsec; dest_r.info->caller_id = r->info->caller_id; memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); prb_final_commit(&e); return prb_record_text_space(&e); } static char setup_text_buf[PRINTKRB_RECORD_MAX] __initdata; static void print_log_buf_usage_stats(void) { unsigned int descs_count = log_buf_len >> PRB_AVGBITS; size_t meta_data_size; meta_data_size = descs_count * (sizeof(struct prb_desc) + sizeof(struct printk_info)); pr_info("log buffer data + meta data: %u + %zu = %zu bytes\n", log_buf_len, meta_data_size, log_buf_len + meta_data_size); } void __init setup_log_buf(int early) { struct printk_info *new_infos; unsigned int new_descs_count; struct prb_desc *new_descs; struct printk_info info; struct printk_record r; unsigned int text_size; size_t new_descs_size; size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very * early, e.g. from setup_arch(), and second - when percpu_areas * are initialised. */ if (!early) set_percpu_data_ready(); if (log_buf != __log_buf) return; if (!early && !new_log_buf_len) log_buf_add_cpu(); if (!new_log_buf_len) { /* Show the memory stats only once. */ if (!early) goto out; return; } new_descs_count = new_log_buf_len >> PRB_AVGBITS; if (new_descs_count == 0) { pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); goto out; } new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { pr_err("log_buf_len: %lu text bytes not available\n", new_log_buf_len); goto out; } new_descs_size = new_descs_count * sizeof(struct prb_desc); new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); if (unlikely(!new_descs)) { pr_err("log_buf_len: %zu desc bytes not available\n", new_descs_size); goto err_free_log_buf; } new_infos_size = new_descs_count * sizeof(struct printk_info); new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); if (unlikely(!new_infos)) { pr_err("log_buf_len: %zu info bytes not available\n", new_infos_size); goto err_free_descs; } prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); prb_init(&printk_rb_dynamic, new_log_buf, ilog2(new_log_buf_len), new_descs, ilog2(new_descs_count), new_infos); local_irq_save(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; prb_for_each_record(0, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } prb = &printk_rb_dynamic; local_irq_restore(flags); /* * Copy any remaining messages that might have appeared from * NMI context after copying but before switching to the * dynamic buffer. */ prb_for_each_record(seq, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); } print_log_buf_usage_stats(); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); return; err_free_descs: memblock_free(new_descs, new_descs_size); err_free_log_buf: memblock_free(new_log_buf, new_log_buf_len); out: print_log_buf_usage_stats(); } static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = true; pr_info("debug: ignoring loglevel setting.\n"); return 0; } early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); static bool suppress_message_printing(int level) { return (level >= console_loglevel && !ignore_loglevel); } #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) { unsigned long lpj; lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ loops_per_msec = (unsigned long long)lpj / 1000 * HZ; get_option(&str, &boot_delay); if (boot_delay > 10 * 1000) boot_delay = 0; pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); return 0; } early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; bool suppress = !is_printk_force_console() && suppress_message_printing(level); if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress) return; k = (unsigned long long)loops_per_msec * boot_delay; timeout = jiffies + msecs_to_jiffies(boot_delay); while (k) { k--; cpu_relax(); /* * use (volatile) jiffies to prevent * compiler reduction; loop termination via jiffies * is secondary and may or may not happen. */ if (time_after(jiffies, timeout)) break; touch_nmi_watchdog(); } } #else static inline void boot_delay_msec(int level) { } #endif static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); static size_t print_syslog(unsigned int level, char *buf) { return sprintf(buf, "<%u>", level); } static size_t print_time(u64 ts, char *buf) { unsigned long rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu]", (unsigned long)ts, rem_nsec / 1000); } #ifdef CONFIG_PRINTK_CALLER static size_t print_caller(u32 id, char *buf) { char caller[12]; snprintf(caller, sizeof(caller), "%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); return sprintf(buf, "[%6s]", caller); } #else #define print_caller(id, buf) 0 #endif static size_t info_print_prefix(const struct printk_info *info, bool syslog, bool time, char *buf) { size_t len = 0; if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len); len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; buf[len] = '\0'; } return len; } /* * Prepare the record for printing. The text is shifted within the given * buffer to avoid a need for another one. The following operations are * done: * * - Add prefix for each line. * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). * - Add a string terminator. * * Since the produced string is always terminated, the maximum possible * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added * prefixes and the newline. The terminator is not counted. The dropped * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) { size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; char prefix[PRINTK_PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; size_t len = 0; char *next; /* * If the message was truncated because the buffer was not large * enough, treat the available text as if it were the full text. */ if (text_len > buf_size) text_len = buf_size; prefix_len = info_print_prefix(r->info, syslog, time, prefix); /* * @text_len: bytes of unprocessed text * @line_len: bytes of current line _without_ newline * @text: pointer to beginning of current line * @len: number of bytes prepared in r->text_buf */ for (;;) { next = memchr(text, '\n', text_len); if (next) { line_len = next - text; } else { /* Drop truncated line(s). */ if (truncated) break; line_len = text_len; } /* * Truncate the text if there is not enough space to add the * prefix and a trailing newline and a terminator. */ if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ if (len + prefix_len + line_len + 1 + 1 > buf_size) break; text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); /* * Increment the prepared length to include the text and * prefix that were just moved+copied. Also increment for the * newline at the end of this line. If this is the last line, * there is no newline, but it will be added immediately below. */ len += prefix_len + line_len + 1; if (text_len == line_len) { /* * This is the last line. Add the trailing newline * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; } /* * Advance beyond the added prefix and the related line with * its newline. */ text += prefix_len + line_len + 1; /* * The remaining text has only decreased by the line with its * newline. * * Note that @text_len can become zero. It happens when @text * ended with a newline (either due to truncation or the * original string ending with "\n\n"). The loop is correctly * repeated and (if not truncated) an empty line with a prefix * will be prepared. */ text_len -= line_len + 1; } /* * If a buffer was provided, it will be terminated. Space for the * string terminator is guaranteed to be available. The terminator is * not counted in the return value. */ if (buf_size > 0) r->text_buf[len] = 0; return len; } static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { char prefix[PRINTK_PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); /* * Each line will be preceded with a prefix. The intermediate * newlines are already within the text, but a final trailing * newline will be added. */ return ((prefix_len * line_count) + info->text_len + 1); } /* * Beginning with @start_seq, find the first record where it and all following * records up to (but not including) @max_seq fit into @size. * * @max_seq is simply an upper bound and does not need to exist. If the caller * does not require an upper bound, -1 can be used for @max_seq. */ static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, bool syslog, bool time) { struct printk_info info; unsigned int line_count; size_t len = 0; u64 seq; /* Determine the size of the records up to @max_seq. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (info.seq >= max_seq) break; len += get_record_print_text_size(&info, line_count, syslog, time); } /* * Adjust the upper bound for the next loop to avoid subtracting * lengths that were never added. */ if (seq < max_seq) max_seq = seq; /* * Move first record forward until length fits into the buffer. Ignore * newest messages that were not counted in the above cycle. Messages * might appear and get lost in the meantime. This is a best effort * that prevents an infinite loop that could occur with a retry. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (len <= size || info.seq >= max_seq) break; len -= get_record_print_text_size(&info, line_count, syslog, time); } return seq; } /* The caller is responsible for making sure @size is greater than 0. */ static int syslog_print(char __user *buf, int size) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); mutex_lock(&syslog_lock); /* * Wait for the @syslog_seq record to be available. @syslog_seq may * change while waiting. */ do { seq = syslog_seq; mutex_unlock(&syslog_lock); /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ mutex_lock(&syslog_lock); if (len) goto out; } while (syslog_seq != seq); /* * Copy records that fit into the buffer. The above cycle makes sure * that the first record is always available. */ do { size_t n; size_t skip; int err; if (!prb_read_valid(prb, syslog_seq, &r)) break; if (r.info->seq != syslog_seq) { /* message is gone, move to next valid one */ syslog_seq = r.info->seq; syslog_partial = 0; } /* * To keep reading/counting partial line consistent, * use printk_time value as of the beginning of a line. */ if (!syslog_partial) syslog_time = printk_time; skip = syslog_partial; n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; if (!n) break; mutex_unlock(&syslog_lock); err = copy_to_user(buf, text + skip, n); mutex_lock(&syslog_lock); if (err) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } while (size); out: mutex_unlock(&syslog_lock); kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; bool time; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, size, true, time); prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); prb_for_each_record(seq, prb, seq, &r) { int textlen; textlen = record_print_text(&r, true, time); if (len + textlen > size) { seq--; break; } if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; if (len < 0) break; } if (clear) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, seq); mutex_unlock(&syslog_lock); } kfree(text); return len; } static void syslog_clear(void) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); mutex_unlock(&syslog_lock); } int do_syslog(int type, char __user *buf, int len, int source) { struct printk_info info; bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: mutex_lock(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ mutex_unlock(&syslog_lock); return 0; } if (info.seq != syslog_seq) { /* messages are gone, move to first one */ syslog_seq = info.seq; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = prb_next_seq(prb) - syslog_seq; } else { bool time = syslog_partial ? syslog_time : printk_time; unsigned int line_count; u64 seq; prb_for_each_info(syslog_seq, prb, seq, &info, &line_count) { error += get_record_print_text_size(&info, line_count, true, time); time = printk_time; } error -= syslog_partial; } mutex_unlock(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ void console_lock_spinning_enable(void) { /* * Do not use spinning in panic(). The panic CPU wants to keep the lock. * Non-panic CPUs abandon the flush anyway. * * Just keep the lockdep annotation. The panic-CPU should avoid * taking console_owner_lock because it might cause a deadlock. * This looks like the easiest way how to prevent false lockdep * reports without handling races a lockless way. */ if (panic_in_progress()) goto lockdep; raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * @cookie: cookie returned from console_srcu_read_lock() * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose both the console_lock and the SRCU read lock if * there was a busy waiter. They must not touch items synchronized by * console_lock or SRCU read lock in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ int console_lock_spinning_disable_and_check(int cookie) { int waiter; /* * Ignore spinning waiters during panic() because they might get stopped * or blocked at any time, * * It is safe because nobody is allowed to start spinning during panic * in the first place. If there has been a waiter then non panic CPUs * might stay spinning. They would get stopped anyway. The panic context * will never start spinning and an interrupted spin on panic CPU will * never continue. */ if (panic_in_progress()) { /* Keep lockdep happy. */ spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, _THIS_IP_); /* * Preserve lockdep lock ordering. Release the SRCU read lock before * releasing the console_lock. */ console_srcu_read_unlock(cookie); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; /* * It's unsafe to spin once a panic has begun. If we are the * panic CPU, we may have already halted the owner of the * console_sem. If we are not the panic CPU, then we should * avoid taking console_sem, so the panic CPU has a better * chance of cleanly acquiring it later. */ if (panic_in_progress()) return 0; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); /* * Update @console_may_schedule for trylock because the previous * owner may have been schedulable. */ console_may_schedule = 0; return 1; } /* * Recursion is tracked separately on each CPU. If NMIs are supported, an * additional NMI context per CPU is also separately tracked. Until per-CPU * is available, a separate "early tracking" is performed. */ static DEFINE_PER_CPU(u8, printk_count); static u8 printk_count_early; #ifdef CONFIG_HAVE_NMI static DEFINE_PER_CPU(u8, printk_count_nmi); static u8 printk_count_nmi_early; #endif /* * Recursion is limited to keep the output sane. printk() should not require * more than 1 level of recursion (allowing, for example, printk() to trigger * a WARN), but a higher value is used in case some printk-internal errors * exist, such as the ringbuffer validation checks failing. */ #define PRINTK_MAX_RECURSION 3 /* * Return a pointer to the dedicated counter for the CPU+context of the * caller. */ static u8 *__printk_recursion_counter(void) { #ifdef CONFIG_HAVE_NMI if (in_nmi()) { if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count_nmi); return &printk_count_nmi_early; } #endif if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count); return &printk_count_early; } /* * Enter recursion tracking. Interrupts are disabled to simplify tracking. * The caller must check the boolean return value to see if the recursion is * allowed. On failure, interrupts are not disabled. * * @recursion_ptr must be a variable of type (u8 *) and is the same variable * that is passed to printk_exit_irqrestore(). */ #define printk_enter_irqsave(recursion_ptr, flags) \ ({ \ bool success = true; \ \ typecheck(u8 *, recursion_ptr); \ local_irq_save(flags); \ (recursion_ptr) = __printk_recursion_counter(); \ if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \ local_irq_restore(flags); \ success = false; \ } else { \ (*(recursion_ptr))++; \ } \ success; \ }) /* Exit recursion tracking, restoring interrupts. */ #define printk_exit_irqrestore(recursion_ptr, flags) \ do { \ typecheck(u8 *, recursion_ptr); \ (*(recursion_ptr))--; \ local_irq_restore(flags); \ } while (0) int printk_delay_msec __read_mostly; static inline void printk_delay(int level) { boot_delay_msec(level); if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : 0x80000000 + smp_processor_id(); } /** * printk_parse_prefix - Parse level and control flags. * * @text: The terminated text message. * @level: A pointer to the current level value, will be updated. * @flags: A pointer to the current printk_info flags, will be updated. * * @level may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @level must be set to * LOGLEVEL_DEFAULT in order to be updated with the parsed value. * * @flags may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @flags will be OR'd with the parsed * value. * * Return: The length of the parsed level and control flags. */ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags) { u16 prefix_len = 0; int kern_level; while (*text) { kern_level = printk_get_level(text); if (!kern_level) break; switch (kern_level) { case '0' ... '7': if (level && *level == LOGLEVEL_DEFAULT) *level = kern_level - '0'; break; case 'c': /* KERN_CONT */ if (flags) *flags |= LOG_CONT; } prefix_len += 2; text += 2; } return prefix_len; } __printf(5, 0) static u16 printk_sprint(char *text, u16 size, int facility, enum printk_info_flags *flags, const char *fmt, va_list args) { u16 text_len; text_len = vscnprintf(text, size, fmt, args); /* Mark and strip a trailing newline. */ if (text_len && text[text_len - 1] == '\n') { text_len--; *flags |= LOG_NEWLINE; } /* Strip log level and control flags. */ if (facility == 0) { u16 prefix_len; prefix_len = printk_parse_prefix(text, NULL, NULL); if (prefix_len) { text_len -= prefix_len; memmove(text, text + prefix_len, text_len); } } trace_console(text, text_len); return text_len; } __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct prb_reserved_entry e; enum printk_info_flags flags = 0; struct printk_record r; unsigned long irqflags; u16 trunc_msg_len = 0; char prefix_buf[8]; u8 *recursion_ptr; u16 reserve_size; va_list args2; u32 caller_id; u16 text_len; int ret = 0; u64 ts_nsec; if (!printk_enter_irqsave(recursion_ptr, irqflags)) return 0; /* * Since the duration of printk() can vary depending on the message * and state of the ringbuffer, grab the timestamp now so that it is * close to the call of printk(). This provides a more deterministic * timestamp with respect to the caller. */ ts_nsec = local_clock(); caller_id = printk_caller_id(); /* * The sprintf needs to come first since the syslog prefix might be * passed in as a parameter. An extra byte must be reserved so that * later the vscnprintf() into the reserved buffer has room for the * terminating '\0', which is not counted by vsnprintf(). */ va_copy(args2, args); reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; va_end(args2); if (reserve_size > PRINTKRB_RECORD_MAX) reserve_size = PRINTKRB_RECORD_MAX; /* Extract log level or control flags. */ if (facility == 0) printk_parse_prefix(&prefix_buf[0], &level, &flags); if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) flags |= LOG_NEWLINE; if (is_printk_force_console()) flags |= LOG_FORCE_CON; if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) { text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &flags, fmt, args); r.info->text_len += text_len; if (flags & LOG_FORCE_CON) r.info->flags |= LOG_FORCE_CON; if (flags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); } else { prb_commit(&e); } ret = text_len; goto out; } } /* * Explicitly initialize the record before every prb_reserve() call. * prb_reserve_in_last() and prb_reserve() purposely invalidate the * structure when they fail. */ prb_rec_init_wr(&r, reserve_size); if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ truncate_msg(&reserve_size, &trunc_msg_len); prb_rec_init_wr(&r, reserve_size + trunc_msg_len); if (!prb_reserve(&e, prb, &r)) goto out; } /* fill message */ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args); if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); r.info->text_len = text_len + trunc_msg_len; r.info->facility = facility; r.info->level = level & 7; r.info->flags = flags & 0x1f; r.info->ts_nsec = ts_nsec; r.info->caller_id = caller_id; if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* A message without a trailing newline can be continued. */ if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); ret = text_len + trunc_msg_len; out: printk_exit_irqrestore(recursion_ptr, irqflags); return ret; } /* * This acts as a one-way switch to allow legacy consoles to print from * the printk() caller context on a panic CPU. It also attempts to flush * the legacy consoles in this context. */ void printk_legacy_allow_panic_sync(void) { struct console_flush_type ft; legacy_allow_panic_sync = true; printk_get_console_flush_type(&ft); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct console_flush_type ft; int printed_len; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; /* * The messages on the panic CPU are the most important. If * non-panic CPUs are generating any messages, they will be * silently dropped. */ if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0; printk_get_console_flush_type(&ft); /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; ft.legacy_offload |= ft.legacy_direct; ft.legacy_direct = false; } printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_direct) { /* * The caller may be holding system-critical or * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers. With the * spinning variant, this context tries to take over the * printing from another printing context. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } if (ft.legacy_offload) defer_console_output(); else wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(_printk); static bool pr_flush(int timeout_ms, bool reset_on_progress); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); #else /* CONFIG_PRINTK */ #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 #define prb_next_seq(rb) 0 static u64 syslog_seq; static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; } static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static void set_user_specified(struct console_cmdline *c, bool user_specified) { if (!user_specified) return; /* * @c console was defined by the user on the command line. * Do not clear when added twice also by SPCR or the device tree. */ c->user_specified = true; /* At least one console defined by the user on the command line. */ console_set_on_cmdline = 1; } static int __add_preferred_console(const char *name, const short idx, const char *devname, char *options, char *brl_options, bool user_specified) { struct console_cmdline *c; int i; if (!name && !devname) return -EINVAL; /* * We use a signed short index for struct console for device drivers to * indicate a not yet assigned index or port. However, a negative index * value is not valid when the console name and index are defined on * the command line. */ if (name && idx < 0) return -EINVAL; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if ((name && strcmp(c->name, name) == 0 && c->index == idx) || (devname && strcmp(c->devname, devname) == 0)) { if (!brl_options) preferred_console = i; set_user_specified(c, user_specified); return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; if (name) strscpy(c->name, name); if (devname) strscpy(c->devname, devname); c->options = options; set_user_specified(c, user_specified); braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { static_assert(sizeof(console_cmdline[0].devname) >= sizeof(console_cmdline[0].name) + 4); char buf[sizeof(console_cmdline[0].devname)]; char *brl_options = NULL; char *ttyname = NULL; char *devname = NULL; char *options; char *s; int idx; /* * console="" or console=null have been suggested as a way to * disable console output. Use ttynull that has been created * for exactly this purpose. */ if (str[0] == 0 || strcmp(str, "null") == 0) { __add_preferred_console("ttynull", 0, NULL, NULL, NULL, true); return 1; } if (_braille_console_setup(&str, &brl_options)) return 1; /* For a DEVNAME:0.0 style console the character device is unknown early */ if (strchr(str, ':')) devname = buf; else ttyname = buf; /* * Decode str into name, index, options. */ if (ttyname && isdigit(str[0])) scnprintf(buf, sizeof(buf), "ttyS%s", str); else strscpy(buf, str); options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strscpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strscpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if ((ttyname && isdigit(*s)) || *s == ',') break; /* @idx will get defined when devname matches. */ if (devname) idx = -1; else idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(ttyname, idx, devname, options, brl_options, true); return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(const char *name, const short idx, char *options) { return __add_preferred_console(name, idx, NULL, options, NULL, false); } /** * match_devname_and_update_preferred_console - Update a preferred console * when matching devname is found. * @devname: DEVNAME:0.0 style device name * @name: Name of the corresponding console driver, e.g. "ttyS" * @idx: Console index, e.g. port number. * * The function checks whether a device with the given @devname is * preferred via the console=DEVNAME:0.0 command line option. * It fills the missing console driver name and console index * so that a later register_console() call could find (match) * and enable this device. * * It might be used when a driver subsystem initializes particular * devices with already known DEVNAME:0.0 style names. And it * could predict which console driver name and index this device * would later get associated with. * * Return: 0 on success, negative error code on failure. */ int match_devname_and_update_preferred_console(const char *devname, const char *name, const short idx) { struct console_cmdline *c = console_cmdline; int i; if (!devname || !strlen(devname) || !name || !strlen(name) || idx < 0) return -EINVAL; for (i = 0; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if (!strcmp(devname, c->devname)) { pr_info("associate the preferred console \"%s\" with \"%s%d\"\n", devname, name, idx); strscpy(c->name, name); c->index = idx; return 0; } } return -ENOENT; } EXPORT_SYMBOL_GPL(match_devname_and_update_preferred_console); bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); static bool printk_console_no_auto_verbose; void console_verbose(void) { if (console_loglevel && !printk_console_no_auto_verbose) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } EXPORT_SYMBOL_GPL(console_verbose); module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); /** * suspend_console - suspend the console subsystem * * This disables printk() while we go into suspend states */ void suspend_console(void) { struct console *con; if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); pr_flush(1000, true); console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags | CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see that they are suspended so that it * is guaranteed that all printing has stopped when this function * completes. */ synchronize_srcu(&console_srcu); } void resume_console(void) { struct console_flush_type ft; struct console *con; if (!console_suspend_enabled) return; console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see they are no longer suspended so * that they are guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); pr_flush(1000, true); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { struct console_flush_type ft; if (!cpuhp_tasks_frozen) { printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } return 0; } /** * console_lock - block the console subsystem from printing * * Acquires a lock which guarantees that no consoles will * be in or enter their write() callback. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); /* On panic, the console_lock must be left to the panic cpu. */ while (other_cpu_in_panic()) msleep(1000); down_console_sem(); console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to block the console subsystem from printing * * Try to acquire a lock which guarantees that no consoles will * be in or enter their write() callback. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { /* On panic, the console_lock must be left to the panic cpu. */ if (other_cpu_in_panic()) return 0; if (down_trylock_console_sem()) return 0; console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); static void __console_unlock(void) { console_locked = 0; up_console_sem(); } #ifdef CONFIG_PRINTK /* * Prepend the message in @pmsg->pbufs->outbuf. This is achieved by shifting * the existing message over and inserting the scratchbuf message. * * @pmsg is the original printk message. * @fmt is the printf format of the message which will prepend the existing one. * * If there is not enough space in @pmsg->pbufs->outbuf, the existing * message text will be sufficiently truncated. * * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated. */ __printf(2, 3) static void console_prepend_message(struct printk_message *pmsg, const char *fmt, ...) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; va_list args; size_t len; va_start(args, fmt); len = vscnprintf(scratchbuf, scratchbuf_sz, fmt, args); va_end(args); /* * Make sure outbuf is sufficiently large before prepending. * Keep at least the prefix when the message must be truncated. * It is a rather theoretical problem when someone tries to * use a minimalist buffer. */ if (WARN_ON_ONCE(len + PRINTK_PREFIX_MAX >= outbuf_sz)) return; if (pmsg->outbuf_len + len >= outbuf_sz) { /* Truncate the message, but keep it terminated. */ pmsg->outbuf_len = outbuf_sz - (len + 1); outbuf[pmsg->outbuf_len] = 0; } memmove(outbuf + len, outbuf, pmsg->outbuf_len + 1); memcpy(outbuf, scratchbuf, len); pmsg->outbuf_len += len; } /* * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. * * @dropped is the dropped count to report in the dropped message. */ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) { console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped); } /* * Prepend the message in @pmsg->pbufs->outbuf with a "replay message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. */ void console_prepend_replay(struct printk_message *pmsg) { console_prepend_message(pmsg, "** replaying previous printk message **\n"); } /* * Read and format the specified record (or a later record if the specified * record is not available). * * @pmsg will contain the formatted result. @pmsg->pbufs must point to a * struct printk_buffers. * * @seq is the record to read and format. If it is not available, the next * valid record is read. * * @is_extended specifies if the message should be formatted for extended * console output. * * @may_supress specifies if records may be skipped based on loglevel. * * Returns false if no record is available. Otherwise true and all fields * of @pmsg are valid. (See the documentation of struct printk_message * for information about the @pmsg fields.) */ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_suppress) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; struct printk_info info; struct printk_record r; size_t len = 0; bool force_con; /* * Formatting extended messages requires a separate buffer, so use the * scratch buffer to read in the ringbuffer text. * * Formatting normal messages is done in-place, so read the ringbuffer * text directly into the output buffer. */ if (is_extended) prb_rec_init_rd(&r, &info, scratchbuf, scratchbuf_sz); else prb_rec_init_rd(&r, &info, outbuf, outbuf_sz); if (!prb_read_valid(prb, seq, &r)) return false; pmsg->seq = r.info->seq; pmsg->dropped = r.info->seq - seq; force_con = r.info->flags & LOG_FORCE_CON; /* * Skip records that are not forced to be printed on consoles and that * has level above the console loglevel. */ if (!force_con && may_suppress && suppress_message_printing(r.info->level)) goto out; if (is_extended) { len = info_print_ext_header(outbuf, outbuf_sz, r.info); len += msg_print_ext_body(outbuf + len, outbuf_sz - len, &r.text_buf[0], r.info->text_len, &r.info->dev_info); } else { len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } out: pmsg->outbuf_len = len; return true; } /* * Legacy console printing from printk() caller context does not respect * raw_spinlock/spinlock nesting. For !PREEMPT_RT the lockdep warning is a * false positive. For PREEMPT_RT the false positive condition does not * occur. * * This map is used to temporarily establish LD_WAIT_SLEEP context for the * console write() callback when legacy printing to avoid false positive * lockdep complaints, thus allowing lockdep to continue to function for * real issues. */ #ifdef CONFIG_PREEMPT_RT static inline void printk_legacy_allow_spinlock_enter(void) { } static inline void printk_legacy_allow_spinlock_exit(void) { } #else static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_SLEEP); static inline void printk_legacy_allow_spinlock_enter(void) { lock_map_acquire_try(&printk_legacy_map); } static inline void printk_legacy_allow_spinlock_exit(void) { lock_map_release(&printk_legacy_map); } #endif /* CONFIG_PREEMPT_RT */ /* * Used as the printk buffers for non-panic, serialized console printing. * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles. * Its usage requires the console_lock held. */ struct printk_buffers printk_shared_pbufs; /* * Print one record for the given console. The record printed is whatever * record is the next available record for the given console. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding both the * console_lock and the SRCU read lock. Otherwise it is set to false. * * @cookie is the cookie from the SRCU read lock. * * Returns false if the given console has no next record to print, otherwise * true. * * Requires the console_lock and the SRCU read lock. */ static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; char *outbuf = &printk_shared_pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &printk_shared_pbufs, }; unsigned long flags; *handover = false; if (!printk_get_next_message(&pmsg, con->seq, is_extended, true)) return false; con->dropped += pmsg.dropped; /* Skip messages of formatted length 0. */ if (pmsg.outbuf_len == 0) { con->seq = pmsg.seq + 1; goto skip; } if (con->dropped && !is_extended) { console_prepend_dropped(&pmsg, con->dropped); con->dropped = 0; } /* Write everything out to the hardware. */ if (force_legacy_kthread() && !panic_in_progress()) { /* * With forced threading this function is in a task context * (either legacy kthread or get_init_console_seq()). There * is no need for concern about printk reentrance, handovers, * or lockdep complaints. */ con->write(con, outbuf, pmsg.outbuf_len); con->seq = pmsg.seq + 1; } else { /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. * * Interrupts are disabled because the hand over to a waiter * must not be interrupted until the hand over is completed * (@console_waiter is cleared). */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); /* Do not trace print latency. */ stop_critical_timings(); printk_legacy_allow_spinlock_enter(); con->write(con, outbuf, pmsg.outbuf_len); printk_legacy_allow_spinlock_exit(); start_critical_timings(); con->seq = pmsg.seq + 1; *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } skip: return true; } #else static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { *handover = false; return false; } static inline void printk_kthreads_check_locked(void) { } #endif /* CONFIG_PRINTK */ /* * Print out all remaining records to all consoles. * * @do_cond_resched is set by the caller. It can be true only in schedulable * context. * * @next_seq is set to the sequence number after the last available record. * The value is valid only when this function returns true. It means that all * usable consoles are completely flushed. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the * console_lock. Otherwise it is set to false. * * Returns true when there was at least one usable console and all messages * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this * is not the panic CPU). Regardless the reason, the caller should assume it * is not useful to immediately try again. * * Requires the console_lock. */ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) { struct console_flush_type ft; bool any_usable = false; struct console *con; bool any_progress; int cookie; *next_seq = 0; *handover = false; do { any_progress = false; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; bool progress; /* * console_flush_all() is only responsible for nbcon * consoles when the nbcon consoles cannot print via * their atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, !do_cond_resched)) continue; any_usable = true; if (flags & CON_NBCON) { progress = nbcon_legacy_emit_next_record(con, handover, cookie, !do_cond_resched); printk_seq = nbcon_seq_read(con); } else { progress = console_emit_next_record(con, handover, cookie); printk_seq = con->seq; } /* * If a handover has occurred, the SRCU read lock * is already released. */ if (*handover) return false; /* Track the next of the highest seq flushed. */ if (printk_seq > *next_seq) *next_seq = printk_seq; if (!progress) continue; any_progress = true; /* Allow panic_cpu to take over the consoles safely. */ if (other_cpu_in_panic()) goto abandon; if (do_cond_resched) cond_resched(); } console_srcu_read_unlock(cookie); } while (any_progress); return any_usable; abandon: console_srcu_read_unlock(cookie); return false; } static void __console_flush_and_unlock(void) { bool do_cond_resched; bool handover; bool flushed; u64 next_seq; /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. Therefore, create * a local to use for the printing loop. */ do_cond_resched = console_may_schedule; do { console_may_schedule = 0; flushed = console_flush_all(do_cond_resched, &next_seq, &handover); if (!handover) __console_unlock(); /* * Abort if there was a failure to flush all messages to all * usable consoles. Either it is not possible to flush (in * which case it would be an infinite loop of retrying) or * another context has taken over printing. */ if (!flushed) break; /* * Some context may have added new records after * console_flush_all() but before unlocking the console. * Re-check if there is a new record to flush. If the trylock * fails, another context is already handling the printing. */ } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); } /** * console_unlock - unblock the legacy console subsystem from printing * * Releases the console_lock which the caller holds to block printing of * the legacy console subsystem. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock() emits the output on * legacy consoles prior to releasing the lock. * * console_unlock(); may be called from any context. */ void console_unlock(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (ft.legacy_direct) __console_flush_and_unlock(); else __console_unlock(); } EXPORT_SYMBOL(console_unlock); /** * console_conditional_schedule - yield the CPU if required * * If the console code is currently allowed to sleep, and * if this CPU should yield the CPU to another task, do * so here. * * Must be called within console_lock();. */ void __sched console_conditional_schedule(void) { if (console_may_schedule) cond_resched(); } EXPORT_SYMBOL(console_conditional_schedule); void console_unblank(void) { bool found_unblank = false; struct console *c; int cookie; /* * First check if there are any consoles implementing the unblank() * callback. If not, there is no reason to continue and take the * console lock, which in particular can be dangerous if * @oops_in_progress is set. */ cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) { found_unblank = true; break; } } console_srcu_read_unlock(cookie); if (!found_unblank) return; /* * Stop console printing because the unblank() callback may * assume the console is not within its write() callback. * * If @oops_in_progress is set, this may be an atomic context. * In that case, attempt a trylock as best-effort. */ if (oops_in_progress) { /* Semaphores are not NMI-safe. */ if (in_nmi()) return; /* * Attempting to trylock the console lock can deadlock * if another CPU was stopped while modifying the * semaphore. "Hope and pray" that this is not the * current situation. */ if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if ((console_srcu_read_flags(c) & CON_ENABLED) && c->unblank) c->unblank(); } console_srcu_read_unlock(cookie); console_unlock(); if (!oops_in_progress) pr_flush(1000, true); } /* * Rewind all consoles to the oldest available record. * * IMPORTANT: The function is safe only when called under * console_lock(). It is not enforced because * it is used as a best effort in panic(). */ static void __console_rewind_all(void) { struct console *c; short flags; int cookie; u64 seq; seq = prb_first_valid_seq(prb); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { flags = console_srcu_read_flags(c); if (flags & CON_NBCON) { nbcon_seq_force(c, seq); } else { /* * This assignment is safe only when called under * console_lock(). On panic, legacy consoles are * only best effort. */ c->seq = seq; } } console_srcu_read_unlock(cookie); } /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(enum con_flush_mode mode) { struct console_flush_type ft; bool handover; u64 next_seq; /* * Ignore the console lock and flush out the messages. Attempting a * trylock would not be useful because: * * - if it is contended, it must be ignored anyway * - console_lock() and console_trylock() block and fail * respectively in panic for non-panic CPUs * - semaphores are not NMI-safe */ /* * If another context is holding the console lock, * @console_may_schedule might be set. Clear it so that * this context does not call cond_resched() while flushing. */ console_may_schedule = 0; if (mode == CONSOLE_REPLAY_ALL) __console_rewind_all(); printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); /* Flush legacy consoles once allowed, even when dangerous. */ if (legacy_allow_panic_sync) console_flush_all(false, &next_seq, &handover); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; int cookie; /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_srcu_read_unlock(cookie); console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can disable console output before suspending a port, and can * re-enable output afterwards. */ void console_stop(struct console *console) { __pr_flush(console, 1000, true); console_list_lock(); console_srcu_write_flags(console, console->flags & ~CON_ENABLED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All contexts must * be able to see that this console is disabled so that (for example) * the caller can suspend the port without risk of another context * using the port. */ synchronize_srcu(&console_srcu); } EXPORT_SYMBOL(console_stop); void console_start(struct console *console) { struct console_flush_type ft; bool is_nbcon; console_list_lock(); console_srcu_write_flags(console, console->flags | CON_ENABLED); is_nbcon = console->flags & CON_NBCON; console_list_unlock(); /* * Ensure that all SRCU list walks have completed. The related * printing context must be able to see it is enabled so that * it is guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (is_nbcon && ft.nbcon_offload) nbcon_kthread_wake(console); else if (ft.legacy_offload) defer_console_output(); __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_start); #ifdef CONFIG_PRINTK static int unregister_console_locked(struct console *console); /* True when system boot is far enough to create printer threads. */ static bool printk_kthreads_ready __ro_after_init; static struct task_struct *printk_legacy_kthread; static bool legacy_kthread_should_wakeup(void) { struct console_flush_type ft; struct console *con; bool ret = false; int cookie; if (kthread_should_stop()) return true; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; /* * The legacy printer thread is only responsible for nbcon * consoles when the nbcon consoles cannot print via their * atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, false)) continue; if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(con); } else { /* * It is safe to read @seq because only this * thread context updates @seq. */ printk_seq = con->seq; } if (prb_read_valid(prb, printk_seq, NULL)) { ret = true; break; } } console_srcu_read_unlock(cookie); return ret; } static int legacy_kthread_func(void *unused) { for (;;) { wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup()); if (kthread_should_stop()) break; console_lock(); __console_flush_and_unlock(); } return 0; } static bool legacy_kthread_create(void) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); if (WARN_ON(IS_ERR(kt))) { pr_err("failed to start legacy printing thread\n"); return false; } printk_legacy_kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(printk_legacy_kthread, -20); return true; } /** * printk_kthreads_shutdown - shutdown all threaded printers * * On system shutdown all threaded printers are stopped. This allows printk * to transition back to atomic printing, thus providing a robust mechanism * for the final shutdown/reboot messages to be output. */ static void printk_kthreads_shutdown(void) { struct console *con; console_list_lock(); if (printk_kthreads_running) { printk_kthreads_running = false; for_each_console(con) { if (con->flags & CON_NBCON) nbcon_kthread_stop(con); } /* * The threads may have been stopped while printing a * backlog. Flush any records left over. */ nbcon_atomic_flush_pending(); } console_list_unlock(); } static struct syscore_ops printk_syscore_ops = { .shutdown = printk_kthreads_shutdown, }; /* * If appropriate, start nbcon kthreads and set @printk_kthreads_running. * If any kthreads fail to start, those consoles are unregistered. * * Must be called under console_list_lock(). */ static void printk_kthreads_check_locked(void) { struct hlist_node *tmp; struct console *con; lockdep_assert_console_list_lock_held(); if (!printk_kthreads_ready) return; if (have_legacy_console || have_boot_console) { if (!printk_legacy_kthread && force_legacy_kthread() && !legacy_kthread_create()) { /* * All legacy consoles must be unregistered. If there * are any nbcon consoles, they will set up their own * kthread. */ hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_NBCON) continue; unregister_console_locked(con); } } } else if (printk_legacy_kthread) { kthread_stop(printk_legacy_kthread); printk_legacy_kthread = NULL; } /* * Printer threads cannot be started as long as any boot console is * registered because there is no way to synchronize the hardware * registers between boot console code and regular console code. * It can only be known that there will be no new boot consoles when * an nbcon console is registered. */ if (have_boot_console || !have_nbcon_console) { /* Clear flag in case all nbcon consoles unregistered. */ printk_kthreads_running = false; return; } if (printk_kthreads_running) return; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_NBCON)) continue; if (!nbcon_kthread_create(con)) unregister_console_locked(con); } printk_kthreads_running = true; } static int __init printk_set_kthreads_ready(void) { register_syscore_ops(&printk_syscore_ops); console_list_lock(); printk_kthreads_ready = true; printk_kthreads_check_locked(); console_list_unlock(); return 0; } early_initcall(printk_set_kthreads_ready); #endif /* CONFIG_PRINTK */ static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); static int console_call_setup(struct console *newcon, char *options) { int err; if (!newcon->setup) return 0; /* Synchronize with possible boot console. */ console_lock(); err = newcon->setup(newcon, options); console_unlock(); return err; } /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected * by either the command line or add_preferred_console() and * setup/enable it. * * Care need to be taken with consoles that are statically * enabled such as netconsole */ static int try_enable_preferred_console(struct console *newcon, bool user_specified) { struct console_cmdline *c; int i, err; for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { /* Console not yet initialized? */ if (!c->name[0]) continue; if (c->user_specified != user_specified) continue; if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return 0; err = console_call_setup(newcon, c->options); if (err) return err; } newcon->flags |= CON_ENABLED; if (i == preferred_console) newcon->flags |= CON_CONSDEV; return 0; } /* * Some consoles, such as pstore and netconsole, can be enabled even * without matching. Accept the pre-enabled consoles only when match() * and setup() had a chance to be called. */ if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) return 0; return -ENOENT; } /* Try to enable the console unconditionally */ static void try_enable_default_console(struct console *newcon) { if (newcon->index < 0) newcon->index = 0; if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; if (newcon->device) newcon->flags |= CON_CONSDEV; } /* Return the starting sequence number for a newly registered console. */ static u64 get_init_console_seq(struct console *newcon, bool bootcon_registered) { struct console *con; bool handover; u64 init_seq; if (newcon->flags & (CON_PRINTBUFFER | CON_BOOT)) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); init_seq = syslog_seq; mutex_unlock(&syslog_lock); } else { /* Begin with next message added to ringbuffer. */ init_seq = prb_next_seq(prb); /* * If any enabled boot consoles are due to be unregistered * shortly, some may not be caught up and may be the same * device as @newcon. Since it is not known which boot console * is the same device, flush all consoles and, if necessary, * start with the message of the enabled boot console that is * the furthest behind. */ if (bootcon_registered && !keep_bootcon) { /* * Hold the console_lock to stop console printing and * guarantee safe access to console->seq. */ console_lock(); /* * Flush all consoles and set the console to start at * the next unprinted sequence number. */ if (!console_flush_all(true, &init_seq, &handover)) { /* * Flushing failed. Just choose the lowest * sequence of the enabled boot consoles. */ /* * If there was a handover, this context no * longer holds the console_lock. */ if (handover) console_lock(); init_seq = prb_next_seq(prb); for_each_console(con) { u64 seq; if (!(con->flags & CON_BOOT) || !(con->flags & CON_ENABLED)) { continue; } if (con->flags & CON_NBCON) seq = nbcon_seq_read(con); else seq = con->seq; if (seq < init_seq) init_seq = seq; } } console_unlock(); } } return init_seq; } #define console_first() \ hlist_entry(console_list.first, struct console, node) static int unregister_console_locked(struct console *console); /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { bool use_device_lock = (newcon->flags & CON_NBCON) && newcon->write_atomic; bool bootcon_registered = false; bool realcon_registered = false; struct console *con; unsigned long flags; u64 init_seq; int err; console_list_lock(); for_each_console(con) { if (WARN(con == newcon, "console '%s%d' already registered\n", con->name, con->index)) { goto unlock; } if (con->flags & CON_BOOT) bootcon_registered = true; else realcon_registered = true; } /* Do not register boot consoles when there already is a real one. */ if ((newcon->flags & CON_BOOT) && realcon_registered) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); goto unlock; } if (newcon->flags & CON_NBCON) { /* * Ensure the nbcon console buffers can be allocated * before modifying any global data. */ if (!nbcon_alloc(newcon)) goto unlock; } /* * See if we want to enable this console driver by default. * * Nope when a console is preferred by the command line, device * tree, or SPCR. * * The first real console with tty binding (driver) wins. More * consoles might get enabled before the right one is found. * * Note that a console with tty binding will have CON_CONSDEV * flag set and will be first in the list. */ if (preferred_console < 0) { if (hlist_empty(&console_list) || !console_first()->device || console_first()->flags & CON_BOOT) { try_enable_default_console(newcon); } } /* See if this console matches one we selected on the command line */ err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) { if (newcon->flags & CON_NBCON) nbcon_free(newcon); goto unlock; } /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { newcon->flags &= ~CON_PRINTBUFFER; } newcon->dropped = 0; init_seq = get_init_console_seq(newcon, bootcon_registered); if (newcon->flags & CON_NBCON) { have_nbcon_console = true; nbcon_seq_force(newcon, init_seq); } else { have_legacy_console = true; newcon->seq = init_seq; } if (newcon->flags & CON_BOOT) have_boot_console = true; /* * If another context is actively using the hardware of this new * console, it will not be aware of the nbcon synchronization. This * is a risk that two contexts could access the hardware * simultaneously if this new console is used for atomic printing * and the other context is still using the hardware. * * Use the driver synchronization to ensure that the hardware is not * in use while this new console transitions to being registered. */ if (use_device_lock) newcon->device_lock(newcon, &flags); /* * Put this console in the list - keep the * preferred driver at the head of the list. */ if (hlist_empty(&console_list)) { /* Ensure CON_CONSDEV is always set for the head. */ newcon->flags |= CON_CONSDEV; hlist_add_head_rcu(&newcon->node, &console_list); } else if (newcon->flags & CON_CONSDEV) { /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(console_first(), console_first()->flags & ~CON_CONSDEV); hlist_add_head_rcu(&newcon->node, &console_list); } else { hlist_add_behind_rcu(&newcon->node, console_list.first); } /* * No need to synchronize SRCU here! The caller does not rely * on all contexts being able to see the new console before * register_console() completes. */ /* This new console is now registered. */ if (use_device_lock) newcon->device_unlock(newcon, flags); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ con_printk(KERN_INFO, newcon, "enabled\n"); if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { struct hlist_node *tmp; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_BOOT) unregister_console_locked(con); } } /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); unlock: console_list_unlock(); } EXPORT_SYMBOL(register_console); /* Must be called under console_list_lock(). */ static int unregister_console_locked(struct console *console) { bool use_device_lock = (console->flags & CON_NBCON) && console->write_atomic; bool found_legacy_con = false; bool found_nbcon_con = false; bool found_boot_con = false; unsigned long flags; struct console *c; int res; lockdep_assert_console_list_lock_held(); con_printk(KERN_INFO, console, "disabled\n"); res = _braille_unregister_console(console); if (res < 0) return res; if (res > 0) return 0; if (!console_is_registered_locked(console)) res = -ENODEV; else if (console_is_usable(console, console->flags, true)) __pr_flush(console, 1000, true); /* Disable it unconditionally */ console_srcu_write_flags(console, console->flags & ~CON_ENABLED); if (res < 0) return res; /* * Use the driver synchronization to ensure that the hardware is not * in use while this console transitions to being unregistered. */ if (use_device_lock) console->device_lock(console, &flags); hlist_del_init_rcu(&console->node); if (use_device_lock) console->device_unlock(console, flags); /* * <HISTORICAL> * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. * </HISTORICAL> * * The above makes no sense as there is no guarantee that the next * console has any device attached. Oh well.... */ if (!hlist_empty(&console_list) && console->flags & CON_CONSDEV) console_srcu_write_flags(console_first(), console_first()->flags | CON_CONSDEV); /* * Ensure that all SRCU list walks have completed. All contexts * must not be able to see this console in the list so that any * exit/cleanup routines can be performed safely. */ synchronize_srcu(&console_srcu); if (console->flags & CON_NBCON) nbcon_free(console); console_sysfs_notify(); if (console->exit) res = console->exit(console); /* * With this console gone, the global flags tracking registered * console types may have changed. Update them. */ for_each_console(c) { if (c->flags & CON_BOOT) found_boot_con = true; if (c->flags & CON_NBCON) found_nbcon_con = true; else found_legacy_con = true; } if (!found_boot_con) have_boot_console = found_boot_con; if (!found_legacy_con) have_legacy_console = found_legacy_con; if (!found_nbcon_con) have_nbcon_console = found_nbcon_con; /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); return res; } int unregister_console(struct console *console) { int res; console_list_lock(); res = unregister_console_locked(console); console_list_unlock(); return res; } EXPORT_SYMBOL(unregister_console); /** * console_force_preferred_locked - force a registered console preferred * @con: The registered console to force preferred. * * Must be called under console_list_lock(). */ void console_force_preferred_locked(struct console *con) { struct console *cur_pref_con; if (!console_is_registered_locked(con)) return; cur_pref_con = console_first(); /* Already preferred? */ if (cur_pref_con == con) return; /* * Delete, but do not re-initialize the entry. This allows the console * to continue to appear registered (via any hlist_unhashed_lockless() * checks), even though it was briefly removed from the console list. */ hlist_del_rcu(&con->node); /* * Ensure that all SRCU list walks have completed so that the console * can be added to the beginning of the console list and its forward * list pointer can be re-initialized. */ synchronize_srcu(&console_srcu); con->flags |= CON_CONSDEV; WARN_ON(!con->device); /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(cur_pref_con, cur_pref_con->flags & ~CON_CONSDEV); hlist_add_head_rcu(&con->node, &console_list); } EXPORT_SYMBOL(console_force_preferred_locked); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistered when the real preferred console is registered. */ static int __init printk_late_init(void) { struct hlist_node *tmp; struct console *con; int ret; console_list_lock(); hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console_locked(con); } } console_list_unlock(); ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); printk_sysctl_init(); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms); unsigned long remaining_jiffies = timeout_jiffies; struct console_flush_type ft; struct console *c; u64 last_diff = 0; u64 printk_seq; short flags; int cookie; u64 diff; u64 seq; /* Sorry, pr_flush() will not work this early. */ if (system_state < SYSTEM_SCHEDULING) return false; might_sleep(); seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { console_lock(); console_unlock(); } for (;;) { unsigned long begin_jiffies; unsigned long slept_jiffies; diff = 0; /* * Hold the console_lock to guarantee safe access to * console->seq. Releasing console_lock flushes more * records in case @seq is still not printed on all * usable consoles. * * Holding the console_lock is not necessary if there * are no legacy or boot consoles. However, such a * console could register at any time. Always hold the * console_lock as a precaution rather than * synchronizing against register_console(). */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (con && con != c) continue; flags = console_srcu_read_flags(c); /* * If consoles are not usable, it cannot be expected * that they make forward progress, so only increment * @diff for usable consoles. */ if (!console_is_usable(c, flags, true) && !console_is_usable(c, flags, false)) { continue; } if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(c); } else { printk_seq = c->seq; } if (printk_seq < seq) diff += seq - printk_seq; } console_srcu_read_unlock(cookie); if (diff != last_diff && reset_on_progress) remaining_jiffies = timeout_jiffies; console_unlock(); /* Note: @diff is 0 if there are no usable consoles. */ if (diff == 0 || remaining_jiffies == 0) break; /* msleep(1) might sleep much longer. Check time by jiffies. */ begin_jiffies = jiffies; msleep(1); slept_jiffies = jiffies - begin_jiffies; remaining_jiffies -= min(slept_jiffies, remaining_jiffies); last_diff = diff; } return (diff == 0); } /** * pr_flush() - Wait for printing threads to catch up. * * @timeout_ms: The maximum time (in ms) to wait. * @reset_on_progress: Reset the timeout if forward progress is seen. * * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 * represents infinite waiting. * * If @reset_on_progress is true, the timeout will be reset whenever any * printer has been seen to make some forward progress. * * Context: Process context. May sleep while acquiring console lock. * Return: true if all usable printers are caught up. */ static bool pr_flush(int timeout_ms, bool reset_on_progress) { return __pr_flush(NULL, timeout_ms, reset_on_progress); } /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { if (force_legacy_kthread()) { if (printk_legacy_kthread) wake_up_interruptible(&legacy_wait); } else { if (console_trylock()) console_unlock(); } } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); static void __wake_up_klogd(int val) { if (!printk_percpu_data_ready()) return; preempt_disable(); /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the wait queue is empty. * * The full memory barrier within wq_has_sleeper() pairs with the full * memory barrier within set_current_state() of * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } /** * wake_up_klogd - Wake kernel logging daemon * * Use this function when new records have been added to the ringbuffer * and the console printing of those records has already occurred or is * known to be handled by some other context. This function will only * wake the logging daemon. * * Context: Any context. */ void wake_up_klogd(void) { __wake_up_klogd(PRINTK_PENDING_WAKEUP); } /** * defer_console_output - Wake kernel logging daemon and trigger * console printing in a deferred context * * Use this function when new records have been added to the ringbuffer, * this context is responsible for console printing those records, but * the current context is not allowed to perform the console printing. * Trigger an irq_work context to perform the console printing. This * function also wakes the logging daemon. * * Context: Any context. */ void defer_console_output(void) { /* * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) { defer_console_output(); } int vprintk_deferred(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); } int _printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) { switch (reason) { case KMSG_DUMP_PANIC: return "Panic"; case KMSG_DUMP_OOPS: return "Oops"; case KMSG_DUMP_EMERG: return "Emergency"; case KMSG_DUMP_SHUTDOWN: return "Shutdown"; default: return "Unknown"; } } EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** * kmsg_dump_desc - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * @desc: a short string to describe what caused the panic or oops. Can be NULL * if no additional description is available. * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { struct kmsg_dumper *dumper; struct kmsg_dump_detail detail = { .reason = reason, .description = desc}; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { enum kmsg_dump_reason max_reason = dumper->max_reason; /* * If client has not provided a specific max_reason, default * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. */ if (max_reason == KMSG_DUMP_UNDEF) { max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : KMSG_DUMP_OOPS; } if (reason > max_reason) continue; /* invoke dumper which will iterate over records */ dumper->dump(dumper, &detail); } rcu_read_unlock(); } /** * kmsg_dump_get_line - retrieve one kmsg log line * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ if (line) { if (!prb_read_valid(prb, iter->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { if (!prb_read_valid_info(prb, iter->cur_seq, &info, &line_count)) { goto out; } l = get_record_print_text_size(&info, line_count, syslog, printk_time); } iter->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len_out: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, char *buf, size_t size, size_t *len_out) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; u64 seq; u64 next_seq; size_t len = 0; bool ret = false; bool time = printk_time; if (!buf || !size) goto out; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ iter->cur_seq = info.seq; } } /* last entry */ if (iter->cur_seq >= iter->next_seq) goto out; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. Pass in size-1 * because this function (by way of record_print_text()) will * not write more than size-1 bytes of text into @buf. */ seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, size - 1, syslog, time); /* * Next kmsg_dump_get_buffer() invocation will dump block of * older records stored right before this one. */ next_seq = seq; prb_rec_init_rd(&r, &info, buf, size); prb_for_each_record(seq, prb, seq, &r) { if (r.info->seq >= iter->next_seq) break; len += record_print_text(&r, syslog, time); /* Adjust record to store to remaining buffer space. */ prb_rec_init_rd(&r, &info, buf + len, size - len); } iter->next_seq = next_seq; ret = true; out: if (len_out) *len_out = len; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind - reset the iterator * @iter: kmsg dump iterator * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); /** * console_try_replay_all - try to replay kernel log on consoles * * Try to obtain lock on console subsystem and replay all * available records in printk buffer on the consoles. * Does nothing if lock is not obtained. * * Context: Any, except for NMI. */ void console_try_replay_all(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (console_trylock()) { __console_rewind_all(); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); /* Consoles are flushed as part of console_unlock(). */ console_unlock(); } } #endif #ifdef CONFIG_SMP static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); bool is_printk_cpu_sync_owner(void) { return (atomic_read(&printk_cpu_sync_owner) == raw_smp_processor_id()); } /** * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant * spinning lock is not owned by any CPU. * * Context: Any context. */ void __printk_cpu_sync_wait(void) { do { cpu_relax(); } while (atomic_read(&printk_cpu_sync_owner) != -1); } EXPORT_SYMBOL(__printk_cpu_sync_wait); /** * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant * spinning lock. * * If no processor has the lock, the calling processor takes the lock and * becomes the owner. If the calling processor is already the owner of the * lock, this function succeeds immediately. * * Context: Any context. Expects interrupts to be disabled. * Return: 1 on success, otherwise 0. */ int __printk_cpu_sync_try_get(void) { int cpu; int old; cpu = smp_processor_id(); /* * Guarantee loads and stores from this CPU when it is the lock owner * are _not_ visible to the previous lock owner. This pairs with * __printk_cpu_sync_put:B. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_put:A can never read from * __printk_cpu_sync_try_get:B. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of the previous CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of this CPU */ old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1, cpu); /* LMM(__printk_cpu_sync_try_get:A) */ if (old == -1) { /* * This CPU is now the owner and begins loading/storing * data: LMM(__printk_cpu_sync_try_get:B) */ return 1; } else if (old == cpu) { /* This CPU is already the owner. */ atomic_inc(&printk_cpu_sync_nested); return 1; } return 0; } EXPORT_SYMBOL(__printk_cpu_sync_try_get); /** * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock. * * The calling processor must be the owner of the lock. * * Context: Any context. Expects interrupts to be disabled. */ void __printk_cpu_sync_put(void) { if (atomic_read(&printk_cpu_sync_nested)) { atomic_dec(&printk_cpu_sync_nested); return; } /* * This CPU is finished loading/storing data: * LMM(__printk_cpu_sync_put:A) */ /* * Guarantee loads and stores from this CPU when it was the * lock owner are visible to the next lock owner. This pairs * with __printk_cpu_sync_try_get:A. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of this CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of the next CPU */ atomic_set_release(&printk_cpu_sync_owner, -1); /* LMM(__printk_cpu_sync_put:B) */ } EXPORT_SYMBOL(__printk_cpu_sync_put); #endif /* CONFIG_SMP */ |
| 314 315 314 316 315 315 315 316 314 315 314 315 315 315 313 316 316 316 316 345 350 315 101 101 38 38 350 316 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) static void retrigger_next_event(void *arg); /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, }, .csd = CSD_INIT(retrigger_next_event, NULL) }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { /* Make sure we catch unsupported clockids */ [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) { if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; else return likely(base->online); } /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * Check if the elected target is suitable considering its next * event and the hotplug state of the current CPU. * * If the elected target is remote and its next event is after the timer * to queue, then a remote reprogram is necessary. However there is no * guarantee the IPI handling the operation would arrive in time to meet * the high resolution deadline. In this case the local CPU becomes a * preferred target, unless it is offline. * * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, struct hrtimer_cpu_base *new_cpu_base, struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; /* * The local CPU clockevent can be reprogrammed. Also get_target_base() * guarantees it is online. */ if (new_cpu_base == this_cpu_base) return true; /* * The offline local CPU can't be the default target if the * next remote target event is after this timer. Keep the * elected new base. An IPI will we issued to reprogram * it as a last resort. */ if (!hrtimer_base_is_online(this_cpu_base)) return true; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires >= new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { if (!hrtimer_base_is_online(base)) { int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); return &per_cpu(hrtimer_bases, cpu); } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ((struct hrtimer *) addr)->function; } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_init(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_init_on_stack(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init_on_stack(timer); trace_hrtimer_init(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. */ if (!hrtimer_hres_active(base) && !tick_nohz_active) return; raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of the function hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns true when the new timer is the leftmost timer in the tree. */ static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; /* * Don't force local queuing if this enqueue happens on a unplugged * CPU after hrtimer_cpu_dying() has been invoked. */ force_local &= this_cpu_base->online; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) { /* * If the current CPU base is online, then the timer is * never queued on a remote CPU if it would be the first * expiring timer there. */ if (hrtimer_base_is_online(this_cpu_base)) return first; /* * Timer was enqueued remote because the current base is * already offline. If the timer is the first to expire, * kick the remote CPU to reprogram the clock event. */ if (first) { struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base; smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd); } return 0; } /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; if (WARN_ON_ONCE(!timer->function)) return; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } #ifdef CONFIG_SMP static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } #else static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } #endif /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling del_timer_sync() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { if (likely(clock_id < MAX_CLOCKS)) { int base = hrtimer_clock_to_base_table[clock_id]; if (likely(base != HRTIMER_MAX_CLOCK_BASES)) return base; } WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) { return HRTIMER_NORESTART; } static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); } static void __hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { __hrtimer_init(timer, clock_id, mode); if (WARN_ON_ONCE(!function)) timer->function = hrtimer_dummy_timeout; else timer->function = function; } /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_init(timer, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_init); /** * hrtimer_setup - initialize a timer to the given clock * @timer: the timer to be initialized * @function: the callback function * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_init(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup); /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized * @function: the callback function * @clock_id: The clock to be used * @mode: The timer mode * * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack * memory. */ void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_init_on_stack(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = timer->function; /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * __hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_init(&sl->timer, clock_id, mode); sl->timer.function = hrtimer_wakeup; sl->task = current; } /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_init_on_stack(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } int hrtimers_cpu_starting(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); /* Clear out any left over state from a CPU down operation */ cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); hrtimers_cpu_starting(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } |
| 173 173 422 422 11 173 173 422 422 385 118 302 11 385 385 40 40 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/refcount_types.h> #include <linux/spinlock_types.h> struct mutex; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check __signed_wrap bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline __signed_wrap void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check __signed_wrap bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) __cond_acquires(lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags) __cond_acquires(lock); #endif /* _LINUX_REFCOUNT_H */ |
| 581 208 524 1008 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for atomic bit * operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H #include <linux/instrumented.h> /** * set_bit - Atomically set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); } /** * clear_bit - Clears a bit in memory * @nr: Bit to clear * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). */ static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); } /** * change_bit - Toggle a bit in memory * @nr: Bit to change * @addr: Address to start counting from * * This is a relaxed atomic operation (no implied memory barriers). * * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); } /** * test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } /** * test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } /** * test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This is an atomic fully-ordered operation (implied full memory barrier). */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 236 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 410 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fs.h> #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 #define DEVCG_ACC_WRITE 4 #define DEVCG_ACC_MASK (DEVCG_ACC_MKNOD | DEVCG_ACC_READ | DEVCG_ACC_WRITE) #define DEVCG_DEV_BLOCK 1 #define DEVCG_DEV_CHAR 2 #define DEVCG_DEV_ALL 4 /* this represents all devices */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access); static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; if (likely(!inode->i_rdev)) return 0; if (S_ISBLK(inode->i_mode)) type = DEVCG_DEV_BLOCK; else if (S_ISCHR(inode->i_mode)) type = DEVCG_DEV_CHAR; else return 0; if (mask & MAY_WRITE) access |= DEVCG_ACC_WRITE; if (mask & MAY_READ) access |= DEVCG_ACC_READ; return devcgroup_check_permission(type, imajor(inode), iminor(inode), access); } static inline int devcgroup_inode_mknod(int mode, dev_t dev) { short type; if (!S_ISBLK(mode) && !S_ISCHR(mode)) return 0; if (S_ISCHR(mode) && dev == WHITEOUT_DEV) return 0; if (S_ISBLK(mode)) type = DEVCG_DEV_BLOCK; else type = DEVCG_DEV_CHAR; return devcgroup_check_permission(type, MAJOR(dev), MINOR(dev), DEVCG_ACC_MKNOD); } #else static inline int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { return 0; } static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } static inline int devcgroup_inode_mknod(int mode, dev_t dev) { return 0; } #endif |
| 94 94 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 | /* SPDX-License-Identifier: GPL-2.0 */ /* * IRQ subsystem internal functions and variables: * * Do not ever include this file from anything else than * kernel/irq/. Do not even think about using any information outside * of this file for your non core code. */ #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/pm_runtime.h> #include <linux/sched/clock.h> #ifdef CONFIG_SPARSE_IRQ # define MAX_SPARSE_IRQS INT_MAX #else # define MAX_SPARSE_IRQS NR_IRQS #endif #define istate core_internal_state__do_not_mess_with_it extern bool noirqdebug; extern struct irqaction chained_action; /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, IRQTF_READY, }; /* * Bit masks for desc->core_internal_state__do_not_mess_with_it * * IRQS_AUTODETECT - autodetection in progress * IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt * detection * IRQS_POLL_INPROGRESS - polling in progress * IRQS_ONESHOT - irq is not unmasked in primary handler * IRQS_REPLAY - irq has been resent and will not be resent * again until the handler has run and cleared * this flag. * IRQS_WAITING - irq is waiting * IRQS_PENDING - irq needs to be resent and should be resent * at the next available opportunity. * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs * IRQS_SYSFS - descriptor has been added to sysfs */ enum { IRQS_AUTODETECT = 0x00000001, IRQS_SPURIOUS_DISABLED = 0x00000002, IRQS_POLL_INPROGRESS = 0x00000008, IRQS_ONESHOT = 0x00000020, IRQS_REPLAY = 0x00000040, IRQS_WAITING = 0x00000080, IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, IRQS_NMI = 0x00002000, IRQS_SYSFS = 0x00004000, }; #include "debug.h" #include "settings.h" extern int __irq_set_trigger(struct irq_desc *desc, unsigned long flags); extern void __disable_irq(struct irq_desc *desc); extern void __enable_irq(struct irq_desc *desc); #define IRQ_RESEND true #define IRQ_NORESEND false #define IRQ_START_FORCE true #define IRQ_START_COND false extern int irq_activate(struct irq_desc *desc); extern int irq_activate_and_startup(struct irq_desc *desc, bool resend); extern int irq_startup(struct irq_desc *desc, bool resend, bool force); extern void irq_shutdown(struct irq_desc *desc); extern void irq_shutdown_and_deactivate(struct irq_desc *desc); extern void irq_enable(struct irq_desc *desc); extern void irq_disable(struct irq_desc *desc); extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu); extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); extern void unmask_threaded_irq(struct irq_desc *desc); extern unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask); #ifdef CONFIG_SPARSE_IRQ static inline void irq_mark_irq(unsigned int irq) { } #else extern void irq_mark_irq(unsigned int irq); #endif extern int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which, bool *state); irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ int check_irq_resend(struct irq_desc *desc, bool inject); void clear_irq_resend(struct irq_desc *desc); void irq_resend_init(struct irq_desc *desc); bool irq_wait_for_poll(struct irq_desc *desc); void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); void wake_threads_waitq(struct irq_desc *desc); #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc); extern void register_handler_proc(unsigned int irq, struct irqaction *action); extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); #else static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void register_handler_proc(unsigned int irq, struct irqaction *action) { } static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif extern bool irq_can_set_affinity_usr(unsigned int irq); extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force); #ifdef CONFIG_SMP extern int irq_setup_affinity(struct irq_desc *desc); #else static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; } #endif /* Inline functions for support of irq chips on slow busses */ static inline void chip_bus_lock(struct irq_desc *desc) { if (unlikely(desc->irq_data.chip->irq_bus_lock)) desc->irq_data.chip->irq_bus_lock(&desc->irq_data); } static inline void chip_bus_sync_unlock(struct irq_desc *desc) { if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock)) desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data); } #define _IRQ_DESC_CHECK (1 << 0) #define _IRQ_DESC_PERCPU (1 << 1) #define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) #define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) #define for_each_action_of_desc(desc, act) \ for (act = desc->action; act; act = act->next) struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check); void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus); static inline struct irq_desc * irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check) { return __irq_get_desc_lock(irq, flags, true, check); } static inline void irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags) { __irq_put_desc_unlock(desc, flags, true); } static inline struct irq_desc * irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check) { return __irq_get_desc_lock(irq, flags, false, check); } static inline void irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) { __irq_put_desc_unlock(desc, flags, false); } #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) static inline unsigned int irqd_get(struct irq_data *d) { return __irqd_to_state(d); } /* * Manipulation functions for irq_data.state */ static inline void irqd_set_move_pending(struct irq_data *d) { __irqd_to_state(d) |= IRQD_SETAFFINITY_PENDING; } static inline void irqd_clr_move_pending(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_SETAFFINITY_PENDING; } static inline void irqd_set_managed_shutdown(struct irq_data *d) { __irqd_to_state(d) |= IRQD_MANAGED_SHUTDOWN; } static inline void irqd_clr_managed_shutdown(struct irq_data *d) { __irqd_to_state(d) &= ~IRQD_MANAGED_SHUTDOWN; } static inline void irqd_clear(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) &= ~mask; } static inline void irqd_set(struct irq_data *d, unsigned int mask) { __irqd_to_state(d) |= mask; } static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) { return __irqd_to_state(d) & mask; } static inline void irq_state_set_disabled(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); } static inline void irq_state_set_masked(struct irq_desc *desc) { irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); } #undef __irqd_to_state static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __this_cpu_inc(desc->kstat_irqs->cnt); __this_cpu_inc(kstat.irqs_sum); } static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __kstat_incr_irqs_this_cpu(desc); desc->tot_count++; } static inline int irq_desc_get_node(struct irq_desc *desc) { return irq_common_data_get_node(&desc->irq_common_data); } static inline int irq_desc_is_chained(struct irq_desc *desc) { return (desc->action && desc->action == &chained_action); } static inline bool irq_is_nmi(struct irq_desc *desc) { return desc->istate & IRQS_NMI; } #ifdef CONFIG_PM_SLEEP bool irq_pm_check_wakeup(struct irq_desc *desc); void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action); #else static inline bool irq_pm_check_wakeup(struct irq_desc *desc) { return false; } static inline void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { } static inline void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } #endif #ifdef CONFIG_IRQ_TIMINGS #define IRQ_TIMINGS_SHIFT 5 #define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT) #define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1) /** * struct irq_timings - irq timings storing structure * @values: a circular buffer of u64 encoded <timestamp,irq> values * @count: the number of elements in the array */ struct irq_timings { u64 values[IRQ_TIMINGS_SIZE]; int count; }; DECLARE_PER_CPU(struct irq_timings, irq_timings); extern void irq_timings_free(int irq); extern int irq_timings_alloc(int irq); static inline void irq_remove_timings(struct irq_desc *desc) { desc->istate &= ~IRQS_TIMINGS; irq_timings_free(irq_desc_get_irq(desc)); } static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) { int irq = irq_desc_get_irq(desc); int ret; /* * We don't need the measurement because the idle code already * knows the next expiry event. */ if (act->flags & __IRQF_TIMER) return; /* * In case the timing allocation fails, we just want to warn, * not fail, so letting the system boot anyway. */ ret = irq_timings_alloc(irq); if (ret) { pr_warn("Failed to allocate irq timing stats for irq%d (%d)", irq, ret); return; } desc->istate |= IRQS_TIMINGS; } extern void irq_timings_enable(void); extern void irq_timings_disable(void); DECLARE_STATIC_KEY_FALSE(irq_timing_enabled); /* * The interrupt number and the timestamp are encoded into a single * u64 variable to optimize the size. * 48 bit time stamp and 16 bit IRQ number is way sufficient. * Who cares an IRQ after 78 hours of idle time? */ static inline u64 irq_timing_encode(u64 timestamp, int irq) { return (timestamp << 16) | irq; } static inline int irq_timing_decode(u64 value, u64 *timestamp) { *timestamp = value >> 16; return value & U16_MAX; } static __always_inline void irq_timings_push(u64 ts, int irq) { struct irq_timings *timings = this_cpu_ptr(&irq_timings); timings->values[timings->count & IRQ_TIMINGS_MASK] = irq_timing_encode(ts, irq); timings->count++; } /* * The function record_irq_time is only called in one place in the * interrupts handler. We want this function always inline so the code * inside is embedded in the function and the static key branching * code can act at the higher level. Without the explicit * __always_inline we can end up with a function call and a small * overhead in the hotpath for nothing. */ static __always_inline void record_irq_time(struct irq_desc *desc) { if (!static_branch_likely(&irq_timing_enabled)) return; if (desc->istate & IRQS_TIMINGS) irq_timings_push(local_clock(), irq_desc_get_irq(desc)); } #else static inline void irq_remove_timings(struct irq_desc *desc) {} static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) {}; static inline void record_irq_time(struct irq_desc *desc) {} #endif /* CONFIG_IRQ_TIMINGS */ #ifdef CONFIG_GENERIC_IRQ_CHIP void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler); #else static inline void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, void __iomem *reg_base, irq_flow_handler_t handler) { } #endif /* CONFIG_GENERIC_IRQ_CHIP */ #ifdef CONFIG_GENERIC_PENDING_IRQ static inline bool irq_can_move_pcntxt(struct irq_data *data) { return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED); } static inline bool irq_move_pending(struct irq_data *data) { return irqd_is_setaffinity_pending(data); } static inline void irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { cpumask_copy(desc->pending_mask, mask); } static inline void irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { cpumask_copy(mask, desc->pending_mask); } static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return desc->pending_mask; } bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear); #else /* CONFIG_GENERIC_PENDING_IRQ */ static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; } static inline bool irq_move_pending(struct irq_data *data) { return false; } static inline void irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { } static inline void irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc) { return NULL; } static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) { return false; } #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve) { irqd_set_activated(data); return 0; } static inline void irq_domain_deactivate_irq(struct irq_data *data) { irqd_clr_activated(data); } #endif static inline struct irq_data *irqd_get_parent_data(struct irq_data *irqd) { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY return irqd->parent_data; #else return NULL; #endif } #ifdef CONFIG_GENERIC_IRQ_DEBUGFS #include <linux/debugfs.h> struct irq_bit_descr { unsigned int mask; char *name; }; #define BIT_MASK_DESCR(m) { .mask = m, .name = #m } void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, const struct irq_bit_descr *sd, int size); void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); static inline void irq_remove_debugfs_entry(struct irq_desc *desc) { debugfs_remove(desc->debugfs_file); kfree(desc->dev_name); } void irq_debugfs_copy_devname(int irq, struct device *dev); # ifdef CONFIG_IRQ_DOMAIN void irq_domain_debugfs_init(struct dentry *root); # else static inline void irq_domain_debugfs_init(struct dentry *root) { } # endif #else /* CONFIG_GENERIC_IRQ_DEBUGFS */ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) { } static inline void irq_remove_debugfs_entry(struct irq_desc *d) { } static inline void irq_debugfs_copy_devname(int irq, struct device *dev) { } #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ |
| 1002 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_FP_H #define __ASM_FP_H #include <asm/errno.h> #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> #ifndef __ASSEMBLY__ #include <linux/bitmap.h> #include <linux/build_bug.h> #include <linux/bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/types.h> /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 /* * The VFP state has 32x64-bit registers and a single 32-bit * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) static inline unsigned long cpacr_save_enable_kernel_sve(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline unsigned long cpacr_save_enable_kernel_sme(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline void cpacr_restore(unsigned long cpacr) { write_sysreg(cpacr, cpacr_el1); isb(); } /* * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by * the architecture. Using this length to allocate worst size buffers * results in excessively large allocations, and this effect is even * more pronounced for SME due to ZA. Define more suitable VLs for * these situations. */ #define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) #define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); extern void fpsimd_signal_preserve_current_state(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_kvm_prepare(void); struct cpu_fp_state { struct user_fpsimd_state *st; void *sve_state; void *sme_state; u64 *svcr; u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; enum fp_type to_save; }; extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); static inline bool thread_sm_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_SM_MASK); } static inline bool thread_za_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK); } /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 /* Offset of FFR in the SVE register dump */ static inline size_t sve_ffr_offset(int vl) { return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; } static inline void *sve_pffr(struct thread_struct *thread) { unsigned int vl; if (system_supports_sme() && thread_sm_enabled(thread)) vl = thread_get_sme_vl(thread); else vl = thread_get_sve_vl(thread); return (char *)thread->sve_state + sve_ffr_offset(vl); } static inline void *thread_zt_state(struct thread_struct *thread) { /* The ZT register state is stored immediately after the ZA state */ unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread)); return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); extern void sve_load_state(void const *state, u32 const *pfpsr, int restore_ffr); extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); extern void sme_set_vq(unsigned long vq_minus_1); extern void sme_save_state(void *state, int zt); extern void sme_load_state(void const *state, int zt); struct arm64_cpu_capabilities; extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and * vice versa). This allows find_next_bit() to be used to find the * _maximum_ VQ not exceeding a certain value. */ static inline unsigned int __vq_to_bit(unsigned int vq) { return SVE_VQ_MAX - vq; } static inline unsigned int __bit_to_vq(unsigned int bit) { return SVE_VQ_MAX - bit; } struct vl_info { enum vec_type type; const char *name; /* For display purposes */ /* Minimum supported vector length across all CPUs */ int min_vl; /* Maximum supported vector length across all CPUs */ int max_vl; int max_virtualisable_vl; /* * Set of available vector lengths, * where length vq encoded as bit __vq_to_bit(vq): */ DECLARE_BITMAP(vq_map, SVE_VQ_MAX); /* Set of vector lengths present on at least one cpu: */ DECLARE_BITMAP(vq_partial_map, SVE_VQ_MAX); }; #ifdef CONFIG_ARM64_SVE extern void sve_alloc(struct task_struct *task, bool flush); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); extern int vec_set_vector_length(struct task_struct *task, enum vec_type type, unsigned long vl, unsigned long flags); extern int sve_set_current_vl(unsigned long arg); extern int sve_get_current_vl(void); static inline void sve_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0); } static inline void sve_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN); } #define sve_cond_update_zcr_vq(val, reg) \ do { \ u64 __zcr = read_sysreg_s((reg)); \ u64 __new = __zcr & ~ZCR_ELx_LEN_MASK; \ __new |= (val) & ZCR_ELx_LEN_MASK; \ if (__zcr != __new) \ write_sysreg_s(__new, (reg)); \ } while (0) /* * Probing and setup functions. * Calls to these functions must be serialised with one another. */ enum vec_type; extern void __init vec_init_vq_map(enum vec_type type); extern void vec_update_vq_map(enum vec_type type); extern int vec_verify_vq_map(enum vec_type type); extern void __init sve_setup(void); extern __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX]; static inline void write_vl(enum vec_type type, u64 val) { u64 tmp; switch (type) { #ifdef CONFIG_ARM64_SVE case ARM64_VEC_SVE: tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif #ifdef CONFIG_ARM64_SME case ARM64_VEC_SME: tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_SMCR_EL1); break; #endif default: WARN_ON_ONCE(1); break; } } static inline int vec_max_vl(enum vec_type type) { return vl_info[type].max_vl; } static inline int vec_max_virtualisable_vl(enum vec_type type) { return vl_info[type].max_virtualisable_vl; } static inline int sve_max_vl(void) { return vec_max_vl(ARM64_VEC_SVE); } static inline int sve_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SVE); } /* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */ static inline bool vq_available(enum vec_type type, unsigned int vq) { return test_bit(__vq_to_bit(vq), vl_info[type].vq_map); } static inline bool sve_vq_available(unsigned int vq) { return vq_available(ARM64_VEC_SVE, vq); } size_t sve_state_size(struct task_struct const *task); #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task, bool flush) { } static inline void fpsimd_release_task(struct task_struct *task) { } static inline void sve_sync_to_fpsimd(struct task_struct *task) { } static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } static inline int sve_max_virtualisable_vl(void) { return 0; } static inline int sve_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sve_get_current_vl(void) { return -EINVAL; } static inline int sve_max_vl(void) { return -EINVAL; } static inline bool sve_vq_available(unsigned int vq) { return false; } static inline void sve_user_disable(void) { BUILD_BUG(); } static inline void sve_user_enable(void) { BUILD_BUG(); } #define sve_cond_update_zcr_vq(val, reg) do { } while (0) static inline void vec_init_vq_map(enum vec_type t) { } static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } static inline size_t sve_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static inline void sme_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); } static inline void sme_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); } static inline void sme_smstart_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); } static inline void sme_smstop_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); } static inline void sme_smstop(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); } extern void __init sme_setup(void); static inline int sme_max_vl(void) { return vec_max_vl(ARM64_VEC_SME); } static inline int sme_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SME); } extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME * specific state for task, given task's currently configured vector * length. */ static inline size_t sme_state_size(struct task_struct const *task) { unsigned int vl = task_get_sme_vl(task); size_t size; size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); if (system_supports_sme2()) size += ZT_SIG_REG_SIZE; return size; } #else static inline void sme_user_disable(void) { BUILD_BUG(); } static inline void sme_user_enable(void) { BUILD_BUG(); } static inline void sme_smstart_sm(void) { } static inline void sme_smstop_sm(void) { } static inline void sme_smstop(void) { } static inline void sme_alloc(struct task_struct *task, bool flush) { } static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } static inline void sme_suspend_exit(void) { } static inline size_t sme_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SME */ /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); #endif #endif |
| 249 269 172 325 181 57 17 17 59 66 140 9 182 358 358 303 78 167 270 291 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_ts_stats)(struct dsa_switch *ds, int port, struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ bool (*support_eee)(struct dsa_switch *ds, int port); int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); bool dsa_supports_eee(struct dsa_switch *ds, int port); #endif |
| 65 65 60 5 304 304 304 267 268 343 65 65 65 65 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) # ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm)) return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_stack); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm) { int i; int ret; int nr_charged = 0; BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Reset stack metadata. */ kasan_unpoison_range(s->addr, THREAD_SIZE); stack = kasan_reset_tag(s->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } tsk->stack_vm_area = s; tsk->stack = stack; return 0; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm = find_vm_area(stack); if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } # else /* !CONFIG_VMAP_STACK */ static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } # endif /* CONFIG_VMAP_STACK */ # else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; #ifdef CONFIG_PER_VMA_LOCK /* SLAB cache for vm_area_struct.lock */ static struct kmem_cache *vma_lock_cachep; static bool vma_lock_alloc(struct vm_area_struct *vma) { vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL); if (!vma->vm_lock) return false; init_rwsem(&vma->vm_lock->lock); vma->vm_lock_seq = UINT_MAX; return true; } static inline void vma_lock_free(struct vm_area_struct *vma) { kmem_cache_free(vma_lock_cachep, vma->vm_lock); } #else /* CONFIG_PER_VMA_LOCK */ static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; } static inline void vma_lock_free(struct vm_area_struct *vma) {} #endif /* CONFIG_PER_VMA_LOCK */ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!vma) return NULL; vma_init(vma, mm); if (!vma_lock_alloc(vma)) { kmem_cache_free(vm_area_cachep, vma); return NULL; } return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) return NULL; ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); /* * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ data_race(memcpy(new, orig, sizeof(*new))); if (!vma_lock_alloc(new)) { kmem_cache_free(vm_area_cachep, new); return NULL; } INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); dup_anon_vma_name(orig, new); return new; } void __vm_area_free(struct vm_area_struct *vma) { vma_numab_state_free(vma); free_anon_vma_name(vma); vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); } #ifdef CONFIG_PER_VMA_LOCK static void vm_area_free_rcu_cb(struct rcu_head *head) { struct vm_area_struct *vma = container_of(head, struct vm_area_struct, vm_rcu); /* The vma should not be locked while being destroyed. */ VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma); __vm_area_free(vma); } #endif void vm_area_free(struct vm_area_struct *vma) { #ifdef CONFIG_PER_VMA_LOCK call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb); #else __vm_area_free(vma); #endif } static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm; int i; vm = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && exe_file_deny_write_access(exe_file)) pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); if (mmap_write_lock_killable(oldmm)) return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(vmi.mas.tree); for_each_vma(vmi, mpnt) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, mpnt->vm_end, GFP_KERNEL); if (retval) goto loop_out; vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ vma_iter_bulk_store(&vmi, tmp); mm->map_count++; if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (vma_is_shared_maywrite(tmp)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = vma_next(&vmi); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); } else { /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, * stop releasing VMAs that have not been duplicated after this * point. */ if (mpnt) { mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&vmi.mas, XA_ZERO_ENTRY); /* Avoid OOM iterating a broken tree */ set_bit(MMF_OOM_SKIP, &mm->flags); } /* * The mm_struct is going to exit, but the locks will be dropped * first. Set the mm_struct as unstable is advisable as it is * not fully initialised. */ set_bit(MMF_UNSTABLE, &mm->flags); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); if (!retval) dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; tsk->migrate_from_cpu = -1; #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) mmget(mm); task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (!mm) { mm = ERR_PTR(-ESRCH); } else if (mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); if (err) uprobe_end_dup_mmap(); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; sched_mm_cid_fork(tsk); return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the file for the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper doesn't perform checks on @pid which makes it useful for pidfds * created via CLONE_PIDFD where @pid has no task attached when the pidfd and * pidfd file are prepared. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { int pidfd; struct file *pidfd_file; pidfd = get_unused_fd_flags(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } /* * anon_inode_getfile() ignores everything outside of the * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. */ pidfd_file->f_flags |= (flags & PIDFD_THREAD); *ret = pidfd_file; return pidfd; } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret: Where to return the pidfd. * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { bool thread = flags & PIDFD_THREAD; if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { int i; for (i = 0; i < RV_PER_TASK_MONITORS; i++) p->rv[i].da_mon.monitoring = false; } #else #define rv_task_fork(p) do {} while (0) #endif /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_sched_cancel_fork: sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); #ifdef CONFIG_PER_VMA_LOCK vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT); #endif mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 | /* * 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 <net/pkt_sched.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 = DEFAULT_TX_QUEUE_LEN; 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); |
| 187 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up(struct file_lock *fl) { wake_up(&fl->c.flc_wait); } static inline bool locks_can_async_lock(const struct file_operations *fops) { return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = READ_ONCE(inode->i_flctx); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include "ipvlan.h" #include <linux/if_vlan.h> #include <linux/if_tap.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static dev_t ipvtap_major; static struct cdev ipvtap_cdev; static const void *ipvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class ipvtap_class = { .name = "ipvtap", .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; struct ipvtap_dev { struct ipvl_dev vlan; struct tap_dev tap; }; static void ipvtap_count_tx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_drps); } static void ipvtap_count_rx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; ipvlan_count_rx(vlan, 0, 0, 0); } static void ipvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; vlan->sfeatures = features; netdev_update_features(vlan->dev); } static int ipvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped; vlantap->tap.update_features = ipvtap_update_features; vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = ipvlan_link_new(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return err; } static void ipvtap_dellink(struct net_device *dev, struct list_head *head) { struct ipvtap_dev *vlan = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlan->tap); ipvlan_link_delete(dev, head); } static void ipvtap_setup(struct net_device *dev) { ipvlan_link_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; dev->priv_flags &= ~IFF_NO_QUEUE; } static struct rtnl_link_ops ipvtap_link_ops __read_mostly = { .kind = "ipvtap", .setup = ipvtap_setup, .newlink = ipvtap_newlink, .dellink = ipvtap_dellink, .priv_size = sizeof(struct ipvtap_dev), }; static int ipvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &ipvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(ipvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); device_destroy(&ipvtap_class, devt); tap_free_minor(ipvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; static int __init ipvtap_init(void) { int err; err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap", THIS_MODULE); if (err) goto out1; err = class_register(&ipvtap_class); if (err) goto out2; err = register_netdevice_notifier(&ipvtap_notifier_block); if (err) goto out3; err = ipvlan_link_register(&ipvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&ipvtap_notifier_block); out3: class_unregister(&ipvtap_class); out2: tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); out1: return err; } module_init(ipvtap_init); static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); class_unregister(&ipvtap_class); tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); } module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); |
| 334 333 334 333 315 317 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_MMAN_H__ #define __ASM_MMAN_H__ #include <uapi/asm/mman.h> #ifndef BUILD_VDSO #include <linux/compiler.h> #include <linux/fs.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/types.h> static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { unsigned long ret = 0; if (system_supports_bti() && (prot & PROT_BTI)) ret |= VM_ARM64_BTI; if (system_supports_mte() && (prot & PROT_MTE)) ret |= VM_MTE; #ifdef CONFIG_ARCH_HAS_PKEYS if (system_supports_poe()) { ret |= pkey & BIT(0) ? VM_PKEY_BIT0 : 0; ret |= pkey & BIT(1) ? VM_PKEY_BIT1 : 0; ret |= pkey & BIT(2) ? VM_PKEY_BIT2 : 0; } #endif return ret; } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags) { /* * Only allow MTE on anonymous mappings as these are guaranteed to be * backed by tags-capable memory. The vm_flags may be overridden by a * filesystem supporting MTE (RAM-based). */ if (system_supports_mte()) { if (flags & (MAP_ANONYMOUS | MAP_HUGETLB)) return VM_MTE_ALLOWED; if (shmem_file(file) || is_file_hugepages(file)) return VM_MTE_ALLOWED; } return 0; } #define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) { unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM; if (system_supports_bti()) supported |= PROT_BTI; if (system_supports_mte()) supported |= PROT_MTE; return (prot & ~supported) == 0; } #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr) static inline bool arch_validate_flags(unsigned long vm_flags) { if (system_supports_mte()) { /* * only allow VM_MTE if VM_MTE_ALLOWED has been set * previously */ if ((vm_flags & VM_MTE) && !(vm_flags & VM_MTE_ALLOWED)) return false; } if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) { /* An executable GCS isn't a good idea. */ if (vm_flags & VM_EXEC) return false; /* The memory management core should prevent this */ VM_WARN_ON(vm_flags & VM_SHARED); } return true; } #define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags) #endif /* !BUILD_VDSO */ #endif /* ! __ASM_MMAN_H__ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004, 2020 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved. */ #ifndef IB_VERBS_H #define IB_VERBS_H #include <linux/ethtool.h> #include <linux/types.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rwsem.h> #include <linux/workqueue.h> #include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> #include <net/ipv6.h> #include <net/ip.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/refcount.h> #include <linux/if_link.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/dim.h> #include <uapi/rdma/ib_user_verbs.h> #include <rdma/rdma_counter.h> #include <rdma/restrack.h> #include <rdma/signature.h> #include <uapi/rdma/rdma_user_ioctl.h> #include <uapi/rdma/ib_user_ioctl_verbs.h> #define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN struct ib_umem_odp; struct ib_uqp_object; struct ib_usrq_object; struct ib_uwq_object; struct rdma_cm_id; struct ib_port; struct hw_stats_device_data; extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; extern struct workqueue_struct *ib_comp_unbound_wq; struct ib_ucq_object; __printf(2, 3) __cold void ibdev_emerg(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_alert(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_crit(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_err(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_warn(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_notice(const struct ib_device *ibdev, const char *format, ...); __printf(2, 3) __cold void ibdev_info(const struct ib_device *ibdev, const char *format, ...); #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define ibdev_dbg(__dev, format, args...) \ dynamic_ibdev_dbg(__dev, format, ##args) #else __printf(2, 3) __cold static inline void ibdev_dbg(const struct ib_device *ibdev, const char *format, ...) {} #endif #define ibdev_level_ratelimited(ibdev_level, ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ if (__ratelimit(&_rs)) \ ibdev_level(ibdev, fmt, ##__VA_ARGS__); \ } while (0) #define ibdev_emerg_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_emerg, ibdev, fmt, ##__VA_ARGS__) #define ibdev_alert_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_alert, ibdev, fmt, ##__VA_ARGS__) #define ibdev_crit_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_crit, ibdev, fmt, ##__VA_ARGS__) #define ibdev_err_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_err, ibdev, fmt, ##__VA_ARGS__) #define ibdev_warn_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_warn, ibdev, fmt, ##__VA_ARGS__) #define ibdev_notice_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_notice, ibdev, fmt, ##__VA_ARGS__) #define ibdev_info_ratelimited(ibdev, fmt, ...) \ ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define ibdev_dbg_ratelimited(ibdev, fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && __ratelimit(&_rs)) \ __dynamic_ibdev_dbg(&descriptor, ibdev, fmt, \ ##__VA_ARGS__); \ } while (0) #else __printf(2, 3) __cold static inline void ibdev_dbg_ratelimited(const struct ib_device *ibdev, const char *format, ...) {} #endif union ib_gid { u8 raw[16]; struct { __be64 subnet_prefix; __be64 interface_id; } global; }; extern union ib_gid zgid; enum ib_gid_type { IB_GID_TYPE_IB = IB_UVERBS_GID_TYPE_IB, IB_GID_TYPE_ROCE = IB_UVERBS_GID_TYPE_ROCE_V1, IB_GID_TYPE_ROCE_UDP_ENCAP = IB_UVERBS_GID_TYPE_ROCE_V2, IB_GID_TYPE_SIZE }; #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { struct net_device __rcu *ndev; struct ib_device *device; union ib_gid gid; enum ib_gid_type gid_type; u16 index; u32 port_num; }; enum { /* set the local administered indication */ IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2, }; enum rdma_transport_type { RDMA_TRANSPORT_IB, RDMA_TRANSPORT_IWARP, RDMA_TRANSPORT_USNIC, RDMA_TRANSPORT_USNIC_UDP, RDMA_TRANSPORT_UNSPECIFIED, }; enum rdma_protocol_type { RDMA_PROTOCOL_IB, RDMA_PROTOCOL_IBOE, RDMA_PROTOCOL_IWARP, RDMA_PROTOCOL_USNIC_UDP }; __attribute_const__ enum rdma_transport_type rdma_node_get_transport(unsigned int node_type); enum rdma_network_type { RDMA_NETWORK_IB, RDMA_NETWORK_ROCE_V1, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) { if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; else if (network_type == RDMA_NETWORK_ROCE_V1) return IB_GID_TYPE_ROCE; else return IB_GID_TYPE_IB; } static inline enum rdma_network_type rdma_gid_attr_network_type(const struct ib_gid_attr *attr) { if (attr->gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; if (attr->gid_type == IB_GID_TYPE_ROCE) return RDMA_NETWORK_ROCE_V1; if (ipv6_addr_v4mapped((struct in6_addr *)&attr->gid)) return RDMA_NETWORK_IPV4; else return RDMA_NETWORK_IPV6; } enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB * messages and can verify the validity of checksum for * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", * which includes support for fast registrations (IB_WR_REG_MR, * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should * also be set by any iWarp device which must support FRs to comply * to the iWarp verbs spec. iWarp devices also support the * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, /* Placement type attributes */ IB_DEVICE_FLUSH_GLOBAL = IB_UVERBS_DEVICE_FLUSH_GLOBAL, IB_DEVICE_FLUSH_PERSISTENT = IB_UVERBS_DEVICE_FLUSH_PERSISTENT, IB_DEVICE_ATOMIC_WRITE = IB_UVERBS_DEVICE_ATOMIC_WRITE, }; enum ib_kernel_cap_flags { /* * This device supports a per-device lkey or stag that can be * used without performing a memory registration for the local * memory. Note that ULPs should never check this flag, but * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ IBK_LOCAL_DMA_LKEY = 1 << 0, /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ IBK_INTEGRITY_HANDOVER = 1 << 1, /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ IBK_ON_DEMAND_PAGING = 1 << 2, /* IB_MR_TYPE_SG_GAPS is supported */ IBK_SG_GAPS_REG = 1 << 3, /* Driver supports RDMA_NLDEV_CMD_DELLINK */ IBK_ALLOW_USER_UNREG = 1 << 4, /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ IBK_UD_TSO = 1 << 6, /* iopib will use the device ops: * get_vf_config * get_vf_guid * get_vf_stats * set_vf_guid * set_vf_link_state */ IBK_VIRTUAL_FUNCTION = 1 << 7, /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ IBK_RDMA_NETDEV_OPA = 1 << 8, }; enum ib_atomic_cap { IB_ATOMIC_NONE, IB_ATOMIC_HCA, IB_ATOMIC_GLOB }; enum ib_odp_general_cap_bits { IB_ODP_SUPPORT = 1 << 0, IB_ODP_SUPPORT_IMPLICIT = 1 << 1, }; enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_SEND = 1 << 0, IB_ODP_SUPPORT_RECV = 1 << 1, IB_ODP_SUPPORT_WRITE = 1 << 2, IB_ODP_SUPPORT_READ = 1 << 3, IB_ODP_SUPPORT_ATOMIC = 1 << 4, IB_ODP_SUPPORT_SRQ_RECV = 1 << 5, }; struct ib_odp_caps { uint64_t general_caps; struct { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; uint32_t xrc_odp_caps; } per_transport_caps; }; struct ib_rss_caps { /* Corresponding bit will be set if qp type from * 'enum ib_qp_type' is supported, e.g. * supported_qpts |= 1 << IB_QPT_UD */ u32 supported_qpts; u32 max_rwq_indirection_tables; u32 max_rwq_indirection_table_size; }; enum ib_tm_cap_flags { /* Support tag matching with rendezvous offload for RC transport */ IB_TM_CAP_RNDV_RC = 1 << 0, }; struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ u32 max_num_tags; /* From enum ib_tm_cap_flags */ u32 flags; /* Max number of outstanding list operations */ u32 max_ops; /* Max number of SGE in tag matching entry */ u32 max_sge; }; struct ib_cq_init_attr { unsigned int cqe; u32 comp_vector; u32 flags; }; enum ib_cq_attr_mask { IB_CQ_MODERATE = 1 << 0, }; struct ib_cq_caps { u16 max_cq_moderation_count; u16 max_cq_moderation_period; }; struct ib_dm_mr_attr { u64 length; u64 offset; u32 access_flags; }; struct ib_dm_alloc_attr { u64 length; u32 alignment; u32 flags; }; struct ib_device_attr { u64 fw_ver; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; u32 vendor_id; u32 vendor_part_id; u32 hw_ver; int max_qp; int max_qp_wr; u64 device_cap_flags; u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; int max_cq; int max_cqe; int max_mr; int max_pd; int max_qp_rd_atom; int max_ee_rd_atom; int max_res_rd_atom; int max_qp_init_rd_atom; int max_ee_init_rd_atom; enum ib_atomic_cap atomic_cap; enum ib_atomic_cap masked_atomic_cap; int max_ee; int max_rdd; int max_mw; int max_raw_ipv6_qp; int max_raw_ethy_qp; int max_mcast_grp; int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; int max_srq; int max_srq_wr; int max_srq_sge; unsigned int max_fast_reg_page_list_len; unsigned int max_pi_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; int sig_prot_cap; int sig_guard_cap; struct ib_odp_caps odp_caps; uint64_t timestamp_mask; uint64_t hca_core_clock; /* in KHZ */ struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ struct ib_tm_caps tm_caps; struct ib_cq_caps cq_caps; u64 max_dm_size; /* Max entries for sgl for optimized performance per READ */ u32 max_sgl_rd; }; enum ib_mtu { IB_MTU_256 = 1, IB_MTU_512 = 2, IB_MTU_1024 = 3, IB_MTU_2048 = 4, IB_MTU_4096 = 5 }; enum opa_mtu { OPA_MTU_8192 = 6, OPA_MTU_10240 = 7 }; static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; case IB_MTU_512: return 512; case IB_MTU_1024: return 1024; case IB_MTU_2048: return 2048; case IB_MTU_4096: return 4096; default: return -1; } } static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) { if (mtu >= 4096) return IB_MTU_4096; else if (mtu >= 2048) return IB_MTU_2048; else if (mtu >= 1024) return IB_MTU_1024; else if (mtu >= 512) return IB_MTU_512; else return IB_MTU_256; } static inline int opa_mtu_enum_to_int(enum opa_mtu mtu) { switch (mtu) { case OPA_MTU_8192: return 8192; case OPA_MTU_10240: return 10240; default: return(ib_mtu_enum_to_int((enum ib_mtu)mtu)); } } static inline enum opa_mtu opa_mtu_int_to_enum(int mtu) { if (mtu >= 10240) return OPA_MTU_10240; else if (mtu >= 8192) return OPA_MTU_8192; else return ((enum opa_mtu)ib_mtu_int_to_enum(mtu)); } enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, IB_PORT_INIT = 2, IB_PORT_ARMED = 3, IB_PORT_ACTIVE = 4, IB_PORT_ACTIVE_DEFER = 5 }; enum ib_port_phys_state { IB_PORT_PHYS_STATE_SLEEP = 1, IB_PORT_PHYS_STATE_POLLING = 2, IB_PORT_PHYS_STATE_DISABLED = 3, IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING = 4, IB_PORT_PHYS_STATE_LINK_UP = 5, IB_PORT_PHYS_STATE_LINK_ERROR_RECOVERY = 6, IB_PORT_PHYS_STATE_PHY_TEST = 7, }; enum ib_port_width { IB_WIDTH_1X = 1, IB_WIDTH_2X = 16, IB_WIDTH_4X = 2, IB_WIDTH_8X = 4, IB_WIDTH_12X = 8 }; static inline int ib_width_enum_to_int(enum ib_port_width width) { switch (width) { case IB_WIDTH_1X: return 1; case IB_WIDTH_2X: return 2; case IB_WIDTH_4X: return 4; case IB_WIDTH_8X: return 8; case IB_WIDTH_12X: return 12; default: return -1; } } enum ib_port_speed { IB_SPEED_SDR = 1, IB_SPEED_DDR = 2, IB_SPEED_QDR = 4, IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, IB_SPEED_HDR = 64, IB_SPEED_NDR = 128, IB_SPEED_XDR = 256, }; enum ib_stat_flag { IB_STAT_FLAG_OPTIONAL = 1 << 0, }; /** * struct rdma_stat_desc * @name - The name of the counter * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL * @priv - Driver private information; Core code should not use */ struct rdma_stat_desc { const char *name; unsigned int flags; const void *priv; }; /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters * should be before being updated again. Stored in jiffies, defaults * to 10 milliseconds, drivers can override the default be specifying * their own value during their allocation routine. * @descs - Array of pointers to static descriptors used for the counters * in directory. * @is_disabled - A bitmap to indicate each counter is currently disabled * or not. * @num_counters - How many hardware counters there are. If name is * shorter than this number, a kernel oops will result. Driver authors * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) * in their code to prevent this. * @value - Array of u64 counters that are accessed by the sysfs code and * filled in by the drivers get_stats routine */ struct rdma_hw_stats { struct mutex lock; /* Protect lifespan and values[] */ unsigned long timestamp; unsigned long lifespan; const struct rdma_stat_desc *descs; unsigned long *is_disabled; int num_counters; u64 value[] __counted_by(num_counters); }; #define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const struct rdma_stat_desc *descs, int num_counters, unsigned long lifespan); void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats); /* Define bits for the various functionality this port needs to be supported by * the core. */ /* Management 0x00000FFF */ #define RDMA_CORE_CAP_IB_MAD 0x00000001 #define RDMA_CORE_CAP_IB_SMI 0x00000002 #define RDMA_CORE_CAP_IB_CM 0x00000004 #define RDMA_CORE_CAP_IW_CM 0x00000008 #define RDMA_CORE_CAP_IB_SA 0x00000010 #define RDMA_CORE_CAP_OPA_MAD 0x00000020 /* Address format 0x000FF000 */ #define RDMA_CORE_CAP_AF_IB 0x00001000 #define RDMA_CORE_CAP_ETH_AH 0x00002000 #define RDMA_CORE_CAP_OPA_AH 0x00004000 #define RDMA_CORE_CAP_IB_GRH_REQUIRED 0x00008000 /* Protocol 0xFFF00000 */ #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000 #define RDMA_CORE_CAP_PROT_USNIC 0x02000000 #define RDMA_CORE_PORT_IB_GRH_REQUIRED (RDMA_CORE_CAP_IB_GRH_REQUIRED \ | RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP) #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_SMI \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_IB_SA \ | RDMA_CORE_CAP_AF_IB) #define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ | RDMA_CORE_CAP_OPA_MAD) #define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET) #define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC) struct ib_port_attr { u64 subnet_prefix; enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; u32 phys_mtu; int gid_tbl_len; unsigned int ip_gids:1; /* This is the value from PortInfo CapabilityMask, defined by IBA */ u32 port_cap_flags; u32 max_msg_sz; u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; u32 sm_lid; u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; u8 subnet_timeout; u8 init_type_reply; u8 active_width; u16 active_speed; u8 phys_state; u16 port_cap_flags2; }; enum ib_device_modify_flags { IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; #define IB_DEVICE_NODE_DESC_MAX 64 struct ib_device_modify { u64 sys_image_guid; char node_desc[IB_DEVICE_NODE_DESC_MAX]; }; enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), IB_PORT_RESET_QKEY_CNTR = (1<<3), IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { u32 set_port_cap_mask; u32 clr_port_cap_mask; u8 init_type; }; enum ib_event_type { IB_EVENT_CQ_ERR, IB_EVENT_QP_FATAL, IB_EVENT_QP_REQ_ERR, IB_EVENT_QP_ACCESS_ERR, IB_EVENT_COMM_EST, IB_EVENT_SQ_DRAINED, IB_EVENT_PATH_MIG, IB_EVENT_PATH_MIG_ERR, IB_EVENT_DEVICE_FATAL, IB_EVENT_PORT_ACTIVE, IB_EVENT_PORT_ERR, IB_EVENT_LID_CHANGE, IB_EVENT_PKEY_CHANGE, IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); struct ib_event { struct ib_device *device; union { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; struct ib_wq *wq; u32 port_num; } element; enum ib_event_type event; }; struct ib_event_handler { struct ib_device *device; void (*handler)(struct ib_event_handler *, struct ib_event *); struct list_head list; }; #define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \ do { \ (_ptr)->device = _device; \ (_ptr)->handler = _handler; \ INIT_LIST_HEAD(&(_ptr)->list); \ } while (0) struct ib_global_route { const struct ib_gid_attr *sgid_attr; union ib_gid dgid; u32 flow_label; u8 sgid_index; u8 hop_limit; u8 traffic_class; }; struct ib_grh { __be32 version_tclass_flow; __be16 paylen; u8 next_hdr; u8 hop_limit; union ib_gid sgid; union ib_gid dgid; }; union rdma_network_hdr { struct ib_grh ibgrh; struct { /* The IB spec states that if it's IPv4, the header * is located in the last 20 bytes of the header. */ u8 reserved[20]; struct iphdr roce4grh; }; }; #define IB_QPN_MASK 0xFFFFFF enum { IB_MULTICAST_QPN = 0xffffff }; #define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) #define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000) enum ib_ah_flags { IB_AH_GRH = 1 }; enum ib_rate { IB_RATE_PORT_CURRENT = 0, IB_RATE_2_5_GBPS = 2, IB_RATE_5_GBPS = 5, IB_RATE_10_GBPS = 3, IB_RATE_20_GBPS = 6, IB_RATE_30_GBPS = 4, IB_RATE_40_GBPS = 7, IB_RATE_60_GBPS = 8, IB_RATE_80_GBPS = 9, IB_RATE_120_GBPS = 10, IB_RATE_14_GBPS = 11, IB_RATE_56_GBPS = 12, IB_RATE_112_GBPS = 13, IB_RATE_168_GBPS = 14, IB_RATE_25_GBPS = 15, IB_RATE_100_GBPS = 16, IB_RATE_200_GBPS = 17, IB_RATE_300_GBPS = 18, IB_RATE_28_GBPS = 19, IB_RATE_50_GBPS = 20, IB_RATE_400_GBPS = 21, IB_RATE_600_GBPS = 22, IB_RATE_800_GBPS = 23, }; /** * ib_rate_to_mult - Convert the IB rate enum to a multiple of the * base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate); /** * ib_rate_to_mbps - Convert the IB rate enum to Mbps. * For example, IB_RATE_2_5_GBPS will be converted to 2500. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); /** * enum ib_mr_type - memory region type * @IB_MR_TYPE_MEM_REG: memory region that is used for * normal registration * @IB_MR_TYPE_SG_GAPS: memory region that is capable to * register any arbitrary sg lists (without * the normal mr constraints - see * ib_map_mr_sg) * @IB_MR_TYPE_DM: memory region that is used for device * memory registration * @IB_MR_TYPE_USER: memory region that is used for the user-space * application * @IB_MR_TYPE_DMA: memory region that is used for DMA operations * without address translations (VA=PA) * @IB_MR_TYPE_INTEGRITY: memory region that is used for * data integrity operations */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SG_GAPS, IB_MR_TYPE_DM, IB_MR_TYPE_USER, IB_MR_TYPE_DMA, IB_MR_TYPE_INTEGRITY, }; enum ib_mr_status_check { IB_MR_CHECK_SIG_STATUS = 1, }; /** * struct ib_mr_status - Memory region status container * * @fail_status: Bitmask of MR checks status. For each * failed check a corresponding status bit is set. * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS * failure. */ struct ib_mr_status { u32 fail_status; struct ib_sig_err sig_err; }; /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. * @mult: multiple to convert. */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); struct rdma_ah_init_attr { struct rdma_ah_attr *ah_attr; u32 flags; struct net_device *xmit_slave; }; enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, }; struct ib_ah_attr { u16 dlid; u8 src_path_bits; }; struct roce_ah_attr { u8 dmac[ETH_ALEN]; }; struct opa_ah_attr { u32 dlid; u8 src_path_bits; bool make_grd; }; struct rdma_ah_attr { struct ib_global_route grh; u8 sl; u8 static_rate; u32 port_num; u8 ah_flags; enum rdma_ah_attr_type type; union { struct ib_ah_attr ib; struct roce_ah_attr roce; struct opa_ah_attr opa; }; }; enum ib_wc_status { IB_WC_SUCCESS, IB_WC_LOC_LEN_ERR, IB_WC_LOC_QP_OP_ERR, IB_WC_LOC_EEC_OP_ERR, IB_WC_LOC_PROT_ERR, IB_WC_WR_FLUSH_ERR, IB_WC_MW_BIND_ERR, IB_WC_BAD_RESP_ERR, IB_WC_LOC_ACCESS_ERR, IB_WC_REM_INV_REQ_ERR, IB_WC_REM_ACCESS_ERR, IB_WC_REM_OP_ERR, IB_WC_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR, IB_WC_LOC_RDD_VIOL_ERR, IB_WC_REM_INV_RD_REQ_ERR, IB_WC_REM_ABORT_ERR, IB_WC_INV_EECN_ERR, IB_WC_INV_EEC_STATE_ERR, IB_WC_FATAL_ERR, IB_WC_RESP_TIMEOUT_ERR, IB_WC_GENERAL_ERR }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { IB_WC_SEND = IB_UVERBS_WC_SEND, IB_WC_RDMA_WRITE = IB_UVERBS_WC_RDMA_WRITE, IB_WC_RDMA_READ = IB_UVERBS_WC_RDMA_READ, IB_WC_COMP_SWAP = IB_UVERBS_WC_COMP_SWAP, IB_WC_FETCH_ADD = IB_UVERBS_WC_FETCH_ADD, IB_WC_BIND_MW = IB_UVERBS_WC_BIND_MW, IB_WC_LOCAL_INV = IB_UVERBS_WC_LOCAL_INV, IB_WC_LSO = IB_UVERBS_WC_TSO, IB_WC_ATOMIC_WRITE = IB_UVERBS_WC_ATOMIC_WRITE, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, IB_WC_FLUSH = IB_UVERBS_WC_FLUSH, /* * Set value of IB_WC_RECV so consumers can test if a completion is a * receive by testing (opcode & IB_WC_RECV). */ IB_WC_RECV = 1 << 7, IB_WC_RECV_RDMA_WITH_IMM }; enum ib_wc_flags { IB_WC_GRH = 1, IB_WC_WITH_IMM = (1<<1), IB_WC_WITH_INVALIDATE = (1<<2), IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { union { u64 wr_id; struct ib_cqe *wr_cqe; }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; struct ib_qp *qp; union { __be32 imm_data; u32 invalidate_rkey; } ex; u32 src_qp; u32 slid; int wc_flags; u16 pkey_index; u8 sl; u8 dlid_path_bits; u32 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; u8 network_hdr_type; }; enum ib_cq_notify_flags { IB_CQ_SOLICITED = 1 << 0, IB_CQ_NEXT_COMP = 1 << 1, IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP, IB_CQ_REPORT_MISSED_EVENTS = 1 << 2, }; enum ib_srq_type { IB_SRQT_BASIC = IB_UVERBS_SRQT_BASIC, IB_SRQT_XRC = IB_UVERBS_SRQT_XRC, IB_SRQT_TM = IB_UVERBS_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) { return srq_type == IB_SRQT_XRC || srq_type == IB_SRQT_TM; } enum ib_srq_attr_mask { IB_SRQ_MAX_WR = 1 << 0, IB_SRQ_LIMIT = 1 << 1, }; struct ib_srq_attr { u32 max_wr; u32 max_sge; u32 srq_limit; }; struct ib_srq_init_attr { void (*event_handler)(struct ib_event *, void *); void *srq_context; struct ib_srq_attr attr; enum ib_srq_type srq_type; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; } xrc; struct { u32 max_num_tags; } tag_matching; }; } ext; }; struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; /* * Maximum number of rdma_rw_ctx structures in flight at a time. * ib_create_qp() will calculate the right amount of needed WRs * and MRs based on this. */ u32 max_rdma_ctxs; }; enum ib_sig_type { IB_SIGNAL_ALL_WR, IB_SIGNAL_REQ_WR }; enum ib_qp_type { /* * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries * here (and in that order) since the MAD layer uses them as * indices into a 2-entry table. */ IB_QPT_SMI, IB_QPT_GSI, IB_QPT_RC = IB_UVERBS_QPT_RC, IB_QPT_UC = IB_UVERBS_QPT_UC, IB_QPT_UD = IB_UVERBS_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, IB_QPT_RAW_PACKET = IB_UVERBS_QPT_RAW_PACKET, IB_QPT_XRC_INI = IB_UVERBS_QPT_XRC_INI, IB_QPT_XRC_TGT = IB_UVERBS_QPT_XRC_TGT, IB_QPT_MAX, IB_QPT_DRIVER = IB_UVERBS_QPT_DRIVER, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer */ IB_QPT_RESERVED1 = 0x1000, IB_QPT_RESERVED2, IB_QPT_RESERVED3, IB_QPT_RESERVED4, IB_QPT_RESERVED5, IB_QPT_RESERVED6, IB_QPT_RESERVED7, IB_QPT_RESERVED8, IB_QPT_RESERVED9, IB_QPT_RESERVED10, }; enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = IB_UVERBS_QP_CREATE_BLOCK_MULTICAST_LOOPBACK, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_INTEGRITY_EN = 1 << 6, IB_QP_CREATE_NETDEV_USE = 1 << 7, IB_QP_CREATE_SCATTER_FCS = IB_UVERBS_QP_CREATE_SCATTER_FCS, IB_QP_CREATE_CVLAN_STRIPPING = IB_UVERBS_QP_CREATE_CVLAN_STRIPPING, IB_QP_CREATE_SOURCE_QPN = 1 << 10, IB_QP_CREATE_PCI_WRITE_END_PADDING = IB_UVERBS_QP_CREATE_PCI_WRITE_END_PADDING, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, }; /* * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler * callback to destroy the passed in QP. */ struct ib_qp_init_attr { /* This callback occurs in workqueue context */ void (*event_handler)(struct ib_event *, void *); void *qp_context; struct ib_cq *send_cq; struct ib_cq *recv_cq; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct ib_qp_cap cap; enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; u32 create_flags; /* * Only needed for special QP types, or when using the RW API. */ u32 port_num; struct ib_rwq_ind_table *rwq_ind_tbl; u32 source_qpn; }; struct ib_qp_open_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; enum ib_qp_type qp_type; }; enum ib_rnr_timeout { IB_RNR_TIMER_655_36 = 0, IB_RNR_TIMER_000_01 = 1, IB_RNR_TIMER_000_02 = 2, IB_RNR_TIMER_000_03 = 3, IB_RNR_TIMER_000_04 = 4, IB_RNR_TIMER_000_06 = 5, IB_RNR_TIMER_000_08 = 6, IB_RNR_TIMER_000_12 = 7, IB_RNR_TIMER_000_16 = 8, IB_RNR_TIMER_000_24 = 9, IB_RNR_TIMER_000_32 = 10, IB_RNR_TIMER_000_48 = 11, IB_RNR_TIMER_000_64 = 12, IB_RNR_TIMER_000_96 = 13, IB_RNR_TIMER_001_28 = 14, IB_RNR_TIMER_001_92 = 15, IB_RNR_TIMER_002_56 = 16, IB_RNR_TIMER_003_84 = 17, IB_RNR_TIMER_005_12 = 18, IB_RNR_TIMER_007_68 = 19, IB_RNR_TIMER_010_24 = 20, IB_RNR_TIMER_015_36 = 21, IB_RNR_TIMER_020_48 = 22, IB_RNR_TIMER_030_72 = 23, IB_RNR_TIMER_040_96 = 24, IB_RNR_TIMER_061_44 = 25, IB_RNR_TIMER_081_92 = 26, IB_RNR_TIMER_122_88 = 27, IB_RNR_TIMER_163_84 = 28, IB_RNR_TIMER_245_76 = 29, IB_RNR_TIMER_327_68 = 30, IB_RNR_TIMER_491_52 = 31 }; enum ib_qp_attr_mask { IB_QP_STATE = 1, IB_QP_CUR_STATE = (1<<1), IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2), IB_QP_ACCESS_FLAGS = (1<<3), IB_QP_PKEY_INDEX = (1<<4), IB_QP_PORT = (1<<5), IB_QP_QKEY = (1<<6), IB_QP_AV = (1<<7), IB_QP_PATH_MTU = (1<<8), IB_QP_TIMEOUT = (1<<9), IB_QP_RETRY_CNT = (1<<10), IB_QP_RNR_RETRY = (1<<11), IB_QP_RQ_PSN = (1<<12), IB_QP_MAX_QP_RD_ATOMIC = (1<<13), IB_QP_ALT_PATH = (1<<14), IB_QP_MIN_RNR_TIMER = (1<<15), IB_QP_SQ_PSN = (1<<16), IB_QP_MAX_DEST_RD_ATOMIC = (1<<17), IB_QP_PATH_MIG_STATE = (1<<18), IB_QP_CAP = (1<<19), IB_QP_DEST_QPN = (1<<20), IB_QP_RESERVED1 = (1<<21), IB_QP_RESERVED2 = (1<<22), IB_QP_RESERVED3 = (1<<23), IB_QP_RESERVED4 = (1<<24), IB_QP_RATE_LIMIT = (1<<25), IB_QP_ATTR_STANDARD_BITS = GENMASK(20, 0), }; enum ib_qp_state { IB_QPS_RESET, IB_QPS_INIT, IB_QPS_RTR, IB_QPS_RTS, IB_QPS_SQD, IB_QPS_SQE, IB_QPS_ERR }; enum ib_mig_state { IB_MIG_MIGRATED, IB_MIG_REARM, IB_MIG_ARMED }; enum ib_mw_type { IB_MW_TYPE_1 = 1, IB_MW_TYPE_2 = 2 }; struct ib_qp_attr { enum ib_qp_state qp_state; enum ib_qp_state cur_qp_state; enum ib_mtu path_mtu; enum ib_mig_state path_mig_state; u32 qkey; u32 rq_psn; u32 sq_psn; u32 dest_qp_num; int qp_access_flags; struct ib_qp_cap cap; struct rdma_ah_attr ah_attr; struct rdma_ah_attr alt_ah_attr; u16 pkey_index; u16 alt_pkey_index; u8 en_sqd_async_notify; u8 sq_draining; u8 max_rd_atomic; u8 max_dest_rd_atomic; u8 min_rnr_timer; u32 port_num; u8 timeout; u8 retry_cnt; u8 rnr_retry; u32 alt_port_num; u8 alt_timeout; u32 rate_limit; struct net_device *xmit_slave; }; enum ib_wr_opcode { /* These are shared with userspace */ IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, IB_WR_SEND = IB_UVERBS_WR_SEND, IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, IB_WR_BIND_MW = IB_UVERBS_WR_BIND_MW, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, IB_WR_MASKED_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, IB_WR_FLUSH = IB_UVERBS_WR_FLUSH, IB_WR_ATOMIC_WRITE = IB_UVERBS_WR_ATOMIC_WRITE, /* These are kernel only and can not be issued by userspace */ IB_WR_REG_MR = 0x20, IB_WR_REG_MR_INTEGRITY, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ IB_WR_RESERVED1 = 0xf0, IB_WR_RESERVED2, IB_WR_RESERVED3, IB_WR_RESERVED4, IB_WR_RESERVED5, IB_WR_RESERVED6, IB_WR_RESERVED7, IB_WR_RESERVED8, IB_WR_RESERVED9, IB_WR_RESERVED10, }; enum ib_send_flags { IB_SEND_FENCE = 1, IB_SEND_SIGNALED = (1<<1), IB_SEND_SOLICITED = (1<<2), IB_SEND_INLINE = (1<<3), IB_SEND_IP_CSUM = (1<<4), /* reserve bits 26-31 for low level drivers' internal use */ IB_SEND_RESERVED_START = (1 << 26), IB_SEND_RESERVED_END = (1 << 31), }; struct ib_sge { u64 addr; u32 length; u32 lkey; }; struct ib_cqe { void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; int send_flags; union { __be32 imm_data; u32 invalidate_rkey; } ex; }; struct ib_rdma_wr { struct ib_send_wr wr; u64 remote_addr; u32 rkey; }; static inline const struct ib_rdma_wr *rdma_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_rdma_wr, wr); } struct ib_atomic_wr { struct ib_send_wr wr; u64 remote_addr; u64 compare_add; u64 swap; u64 compare_add_mask; u64 swap_mask; u32 rkey; }; static inline const struct ib_atomic_wr *atomic_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_atomic_wr, wr); } struct ib_ud_wr { struct ib_send_wr wr; struct ib_ah *ah; void *header; int hlen; int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u32 port_num; /* valid for DR SMPs on switch only */ }; static inline const struct ib_ud_wr *ud_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_ud_wr, wr); } struct ib_reg_wr { struct ib_send_wr wr; struct ib_mr *mr; u32 key; int access; }; static inline const struct ib_reg_wr *reg_wr(const struct ib_send_wr *wr) { return container_of(wr, struct ib_reg_wr, wr); } struct ib_recv_wr { struct ib_recv_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; }; enum ib_access_flags { IB_ACCESS_LOCAL_WRITE = IB_UVERBS_ACCESS_LOCAL_WRITE, IB_ACCESS_REMOTE_WRITE = IB_UVERBS_ACCESS_REMOTE_WRITE, IB_ACCESS_REMOTE_READ = IB_UVERBS_ACCESS_REMOTE_READ, IB_ACCESS_REMOTE_ATOMIC = IB_UVERBS_ACCESS_REMOTE_ATOMIC, IB_ACCESS_MW_BIND = IB_UVERBS_ACCESS_MW_BIND, IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED, IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND, IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB, IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING, IB_ACCESS_FLUSH_GLOBAL = IB_UVERBS_ACCESS_FLUSH_GLOBAL, IB_ACCESS_FLUSH_PERSISTENT = IB_UVERBS_ACCESS_FLUSH_PERSISTENT, IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE, IB_ACCESS_SUPPORTED = ((IB_ACCESS_FLUSH_PERSISTENT << 1) - 1) | IB_ACCESS_OPTIONAL, }; /* * XXX: these are apparently used for ->rereg_user_mr, no idea why they * are hidden here instead of a uapi header! */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), IB_MR_REREG_ACCESS = (1<<2), IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; struct ib_umem; enum rdma_remove_reason { /* * Userspace requested uobject deletion or initial try * to remove uobject via cleanup. Call could fail */ RDMA_REMOVE_DESTROY, /* Context deletion. This call should delete the actual object itself */ RDMA_REMOVE_CLOSE, /* Driver is being hot-unplugged. This call should delete the actual object itself */ RDMA_REMOVE_DRIVER_REMOVE, /* uobj is being cleaned-up before being committed */ RDMA_REMOVE_ABORT, /* The driver failed to destroy the uobject and is being disconnected */ RDMA_REMOVE_DRIVER_FAILURE, }; struct ib_rdmacg_object { #ifdef CONFIG_CGROUP_RDMA struct rdma_cgroup *cg; /* owner rdma cgroup */ #endif }; struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; struct ib_rdmacg_object cg_obj; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; struct xarray mmap_xa; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ /* ufile & ucontext owning this object */ struct ib_uverbs_file *ufile; /* FIXME, save memory: ufile->context == context */ struct ib_ucontext *context; /* associated user context */ void *object; /* containing object */ struct list_head list; /* link to context's list */ struct ib_rdmacg_object cg_obj; /* rdmacg object */ int id; /* index into kernel idr */ struct kref ref; atomic_t usecnt; /* protects exclusive access */ struct rcu_head rcu; /* kfree_rcu() overhead */ const struct uverbs_api_object *uapi_object; }; struct ib_udata { const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; struct ib_pd { u32 local_dma_lkey; u32 flags; struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ u32 unsafe_global_rkey; /* * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; struct rdma_restrack_entry res; }; struct ib_xrcd { struct ib_device *device; atomic_t usecnt; /* count all exposed resources */ struct inode *inode; struct rw_semaphore tgt_qps_rwsem; struct xarray tgt_qps; }; struct ib_ah { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; const struct ib_gid_attr *sgid_attr; enum rdma_ah_attr_type type; }; typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ IB_POLL_LAST_POOL_TYPE = IB_POLL_UNBOUND_WORKQUEUE, IB_POLL_DIRECT, /* caller context, no hw completions */ }; struct ib_cq { struct ib_device *device; struct ib_ucq_object *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; unsigned int cqe_used; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; struct list_head pool_entry; union { struct irq_poll iop; struct work_struct work; }; struct workqueue_struct *comp_wq; struct dim *dim; /* updated only by trace points */ ktime_t timestamp; u8 interrupt:1; u8 shared:1; unsigned int comp_vector; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_srq { struct ib_device *device; struct ib_pd *pd; struct ib_usrq_object *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; enum ib_srq_type srq_type; atomic_t usecnt; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; u32 srq_num; } xrc; }; } ext; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; enum ib_raw_packet_caps { /* * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ IB_RAW_PACKET_CAP_CVLAN_STRIPPING = IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, /* * Scatter FCS field of an incoming packet to host memory is supported. */ IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, /* * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { IB_WQT_RQ = IB_UVERBS_WQT_RQ, }; enum ib_wq_state { IB_WQS_RESET, IB_WQS_RDY, IB_WQS_ERR }; struct ib_wq { struct ib_device *device; struct ib_uwq_object *uobject; void *wq_context; void (*event_handler)(struct ib_event *, void *); struct ib_pd *pd; struct ib_cq *cq; u32 wq_num; enum ib_wq_state state; enum ib_wq_type wq_type; atomic_t usecnt; }; enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = IB_UVERBS_WQ_FLAGS_CVLAN_STRIPPING, IB_WQ_FLAGS_SCATTER_FCS = IB_UVERBS_WQ_FLAGS_SCATTER_FCS, IB_WQ_FLAGS_DELAY_DROP = IB_UVERBS_WQ_FLAGS_DELAY_DROP, IB_WQ_FLAGS_PCI_WRITE_END_PADDING = IB_UVERBS_WQ_FLAGS_PCI_WRITE_END_PADDING, }; struct ib_wq_init_attr { void *wq_context; enum ib_wq_type wq_type; u32 max_wr; u32 max_sge; struct ib_cq *cq; void (*event_handler)(struct ib_event *, void *); u32 create_flags; /* Use enum ib_wq_flags */ }; enum ib_wq_attr_mask { IB_WQ_STATE = 1 << 0, IB_WQ_CUR_STATE = 1 << 1, IB_WQ_FLAGS = 1 << 2, }; struct ib_wq_attr { enum ib_wq_state wq_state; enum ib_wq_state curr_wq_state; u32 flags; /* Use enum ib_wq_flags */ u32 flags_mask; /* Use enum ib_wq_flags */ }; struct ib_rwq_ind_table { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; u32 ind_tbl_num; u32 log_ind_tbl_size; struct ib_wq **ind_tbl; }; struct ib_rwq_ind_table_init_attr { u32 log_ind_tbl_size; /* Each entry is a pointer to Receive Work Queue */ struct ib_wq **ind_tbl; }; enum port_pkey_state { IB_PORT_PKEY_NOT_VALID = 0, IB_PORT_PKEY_VALID = 1, IB_PORT_PKEY_LISTED = 2, }; struct ib_qp_security; struct ib_port_pkey { enum port_pkey_state state; u16 pkey_index; u32 port_num; struct list_head qp_list; struct list_head to_error_list; struct ib_qp_security *sec; }; struct ib_ports_pkeys { struct ib_port_pkey main; struct ib_port_pkey alt; }; struct ib_qp_security { struct ib_qp *qp; struct ib_device *dev; /* Hold this mutex when changing port and pkey settings. */ struct mutex mutex; struct ib_ports_pkeys *ports_pkeys; /* A list of all open shared QP handles. Required to enforce security * properly for all users of a shared QP. */ struct list_head shared_qp_list; void *security; bool destroying; atomic_t error_list_count; struct completion error_complete; int error_comps_pending; }; /* * @max_write_sge: Maximum SGE elements per RDMA WRITE request. * @max_read_sge: Maximum SGE elements per RDMA READ request. */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; spinlock_t mr_lock; int mrs_used; struct list_head rdma_mrs; struct list_head sig_mrs; struct ib_srq *srq; struct completion srq_completion; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; struct ib_qp *real_qp; struct ib_uqp_object *uobject; void (*event_handler)(struct ib_event *, void *); void (*registered_event_handler)(struct ib_event *, void *); void *qp_context; /* sgid_attrs associated with the AV's */ const struct ib_gid_attr *av_sgid_attr; const struct ib_gid_attr *alt_path_sgid_attr; u32 qp_num; u32 max_write_sge; u32 max_read_sge; enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u32 port; bool integrity_en; /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; /* The counter the qp is bind to */ struct rdma_counter *counter; }; struct ib_dm { struct ib_device *device; u32 length; u32 flags; struct ib_uobject *uobject; atomic_t usecnt; }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; u32 lkey; u32 rkey; u64 iova; u64 length; unsigned int page_size; enum ib_mr_type type; bool need_inval; union { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; struct ib_dm *dm; struct ib_sig_attrs *sig_attrs; /* only for IB_MR_TYPE_INTEGRITY MRs */ /* * Implementation details of the RDMA core, don't use in drivers: */ struct rdma_restrack_entry res; }; struct ib_mw { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; enum ib_mw_type type; }; /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ IB_FLOW_ATTR_NORMAL = 0x0, /* default unicast and multicast rule - * receive all Eth traffic which isn't steered to any QP */ IB_FLOW_ATTR_ALL_DEFAULT = 0x1, /* default multicast rule - * receive all Eth multicast traffic which isn't steered to any QP */ IB_FLOW_ATTR_MC_DEFAULT = 0x2, /* sniffer rule - receive all port traffic */ IB_FLOW_ATTR_SNIFFER = 0x3 }; /* Supported steering header types */ enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, IB_FLOW_SPEC_IPV6 = 0x31, IB_FLOW_SPEC_ESP = 0x34, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41, IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50, IB_FLOW_SPEC_GRE = 0x51, IB_FLOW_SPEC_MPLS = 0x60, IB_FLOW_SPEC_INNER = 0x100, /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, IB_FLOW_SPEC_ACTION_HANDLE = 0x1002, IB_FLOW_SPEC_ACTION_COUNT = 0x1003, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 10 enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_EGRESS = 1UL << 2, /* Egress flow */ IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 3 /* Must be last */ }; struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; __be16 ether_type; __be16 vlan_tag; }; struct ib_flow_spec_eth { u32 type; u16 size; struct ib_flow_eth_filter val; struct ib_flow_eth_filter mask; }; struct ib_flow_ib_filter { __be16 dlid; __u8 sl; }; struct ib_flow_spec_ib { u32 type; u16 size; struct ib_flow_ib_filter val; struct ib_flow_ib_filter mask; }; /* IPv4 header flags */ enum ib_ipv4_flags { IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */ IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the last have this flag set */ }; struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; u8 proto; u8 tos; u8 ttl; u8 flags; }; struct ib_flow_spec_ipv4 { u32 type; u16 size; struct ib_flow_ipv4_filter val; struct ib_flow_ipv4_filter mask; }; struct ib_flow_ipv6_filter { u8 src_ip[16]; u8 dst_ip[16]; __be32 flow_label; u8 next_hdr; u8 traffic_class; u8 hop_limit; } __packed; struct ib_flow_spec_ipv6 { u32 type; u16 size; struct ib_flow_ipv6_filter val; struct ib_flow_ipv6_filter mask; }; struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; }; struct ib_flow_spec_tcp_udp { u32 type; u16 size; struct ib_flow_tcp_udp_filter val; struct ib_flow_tcp_udp_filter mask; }; struct ib_flow_tunnel_filter { __be32 tunnel_id; }; /* ib_flow_spec_tunnel describes the Vxlan tunnel * the tunnel_id from val has the vni value */ struct ib_flow_spec_tunnel { u32 type; u16 size; struct ib_flow_tunnel_filter val; struct ib_flow_tunnel_filter mask; }; struct ib_flow_esp_filter { __be32 spi; __be32 seq; }; struct ib_flow_spec_esp { u32 type; u16 size; struct ib_flow_esp_filter val; struct ib_flow_esp_filter mask; }; struct ib_flow_gre_filter { __be16 c_ks_res0_ver; __be16 protocol; __be32 key; }; struct ib_flow_spec_gre { u32 type; u16 size; struct ib_flow_gre_filter val; struct ib_flow_gre_filter mask; }; struct ib_flow_mpls_filter { __be32 tag; }; struct ib_flow_spec_mpls { u32 type; u16 size; struct ib_flow_mpls_filter val; struct ib_flow_mpls_filter mask; }; struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; u32 tag_id; }; struct ib_flow_spec_action_drop { enum ib_flow_spec_type type; u16 size; }; struct ib_flow_spec_action_handle { enum ib_flow_spec_type type; u16 size; struct ib_flow_action *act; }; enum ib_counters_description { IB_COUNTER_PACKETS, IB_COUNTER_BYTES, }; struct ib_flow_spec_action_count { enum ib_flow_spec_type type; u16 size; struct ib_counters *counters; }; union ib_flow_spec { struct { u32 type; u16 size; }; struct ib_flow_spec_eth eth; struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; struct ib_flow_spec_ipv6 ipv6; struct ib_flow_spec_tunnel tunnel; struct ib_flow_spec_esp esp; struct ib_flow_spec_gre gre; struct ib_flow_spec_mpls mpls; struct ib_flow_spec_action_tag flow_tag; struct ib_flow_spec_action_drop drop; struct ib_flow_spec_action_handle action; struct ib_flow_spec_action_count flow_count; }; struct ib_flow_attr { enum ib_flow_attr_type type; u16 size; u16 priority; u32 flags; u8 num_of_specs; u32 port; union ib_flow_spec flows[]; }; struct ib_flow { struct ib_qp *qp; struct ib_device *device; struct ib_uobject *uobject; }; enum ib_flow_action_type { IB_FLOW_ACTION_UNSPECIFIED, IB_FLOW_ACTION_ESP = 1, }; struct ib_flow_action_attrs_esp_keymats { enum ib_uverbs_flow_action_esp_keymat protocol; union { struct ib_uverbs_flow_action_esp_keymat_aes_gcm aes_gcm; } keymat; }; struct ib_flow_action_attrs_esp_replays { enum ib_uverbs_flow_action_esp_replay protocol; union { struct ib_uverbs_flow_action_esp_replay_bmp bmp; } replay; }; enum ib_flow_action_attrs_esp_flags { /* All user-space flags at the top: Use enum ib_uverbs_flow_action_esp_flags * This is done in order to share the same flags between user-space and * kernel and spare an unnecessary translation. */ /* Kernel flags */ IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED = 1ULL << 32, IB_FLOW_ACTION_ESP_FLAGS_MOD_ESP_ATTRS = 1ULL << 33, }; struct ib_flow_spec_list { struct ib_flow_spec_list *next; union ib_flow_spec spec; }; struct ib_flow_action_attrs_esp { struct ib_flow_action_attrs_esp_keymats *keymat; struct ib_flow_action_attrs_esp_replays *replay; struct ib_flow_spec_list *encap; /* Used only if IB_FLOW_ACTION_ESP_FLAGS_ESN_TRIGGERED is enabled. * Value of 0 is a valid value. */ u32 esn; u32 spi; u32 seq; u32 tfc_pad; /* Use enum ib_flow_action_attrs_esp_flags */ u64 flags; u64 hard_limit_pkts; }; struct ib_flow_action { struct ib_device *device; struct ib_uobject *uobject; enum ib_flow_action_type type; atomic_t usecnt; }; struct ib_mad; enum ib_process_mad_flags { IB_MAD_IGNORE_MKEY = 1, IB_MAD_IGNORE_BKEY = 2, IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY }; enum ib_mad_result { IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */ }; struct ib_port_cache { u64 subnet_prefix; struct ib_pkey_cache *pkey; struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; enum ib_port_state last_port_state; }; struct ib_port_immutable { int pkey_tbl_len; int gid_tbl_len; u32 core_cap_flags; u32 max_mad_size; }; struct ib_port_data { struct ib_device *ib_dev; struct ib_port_immutable immutable; spinlock_t pkey_list_lock; spinlock_t netdev_lock; struct list_head pkey_list; struct ib_port_cache cache; struct net_device __rcu *netdev; netdevice_tracker netdev_tracker; struct hlist_node ndev_hash_link; struct rdma_port_counter port_counter; struct ib_port *sysfs; }; /* rdma netdev type - specifies protocol type */ enum rdma_netdev_t { RDMA_NETDEV_OPA_VNIC, RDMA_NETDEV_IPOIB, }; /** * struct rdma_netdev - rdma netdev * For cases where netstack interfacing is required. */ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u32 port_num; int mtu; /* * cleanup function must be specified. * FIXME: This is only used for OPA_VNIC and that usage should be * removed too. */ void (*free_rdma_netdev)(struct net_device *netdev); /* control functions */ void (*set_id)(struct net_device *netdev, int id); /* send packet */ int (*send)(struct net_device *dev, struct sk_buff *skb, struct ib_ah *address, u32 dqpn); /* multicast */ int (*attach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid, int set_qkey, u32 qkey); int (*detach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid); /* timeout */ void (*tx_timeout)(struct net_device *dev, unsigned int txqueue); }; struct rdma_netdev_alloc_params { size_t sizeof_priv; unsigned int txqs; unsigned int rxqs; void *param; int (*initialize_rdma_netdev)(struct ib_device *device, u32 port_num, struct net_device *netdev, void *param); }; struct ib_odp_counters { atomic64_t faults; atomic64_t faults_handled; atomic64_t invalidations; atomic64_t invalidations_handled; atomic64_t prefetch; }; struct ib_counters { struct ib_device *device; struct ib_uobject *uobject; /* num of objects attached */ atomic_t usecnt; }; struct ib_counters_read_attr { u64 *counters_buff; u32 ncounters; u32 flags; /* use enum ib_read_counters_flags */ }; struct uverbs_attr_bundle; struct iw_cm_id; struct iw_cm_conn_param; #define INIT_RDMA_OBJ_SIZE(ib_struct, drv_struct, member) \ .size_##ib_struct = \ (sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof(struct drv_struct, member)) + \ BUILD_BUG_ON_ZERO( \ !__same_type(((struct drv_struct *)NULL)->member, \ struct ib_struct))) #define rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, gfp) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ gfp, false)) #define rdma_zalloc_drv_obj_numa(ib_dev, ib_type) \ ((struct ib_type *)rdma_zalloc_obj(ib_dev, ib_dev->ops.size_##ib_type, \ GFP_KERNEL, true)) #define rdma_zalloc_drv_obj(ib_dev, ib_type) \ rdma_zalloc_drv_obj_gfp(ib_dev, ib_type, GFP_KERNEL) #define DECLARE_RDMA_OBJ_SIZE(ib_struct) size_t size_##ib_struct struct rdma_user_mmap_entry { struct kref ref; struct ib_ucontext *ucontext; unsigned long start_pgoff; size_t npages; bool driver_removed; }; /* Return the offset (in bytes) the user should pass to libc's mmap() */ static inline u64 rdma_user_mmap_get_offset(const struct rdma_user_mmap_entry *entry) { return (u64)entry->start_pgoff << PAGE_SHIFT; } /** * struct ib_device_ops - InfiniBand device operations * This structure defines all the InfiniBand device operations, providers will * need to define the supported operations, otherwise they will be set to null. */ struct ib_device_ops { struct module *owner; enum rdma_driver_id driver_id; u32 uverbs_abi_ver; unsigned int uverbs_no_driver_id_binding:1; /* * NOTE: New drivers should not make use of device_group; instead new * device parameter should be exposed via netlink command. This * mechanism exists only for existing drivers. */ const struct attribute_group *device_group; const struct attribute_group **port_groups; int (*post_send)(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr); int (*post_recv)(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); void (*drain_rq)(struct ib_qp *qp); void (*drain_sq)(struct ib_qp *qp); int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int (*peek_cq)(struct ib_cq *cq, int wc_cnt); int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags); int (*post_srq_recv)(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int (*process_mad)(struct ib_device *device, int process_mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad, size_t *out_mad_size, u16 *out_mad_pkey_index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); int (*modify_device)(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); void (*get_dev_fw_str)(struct ib_device *device, char *str); const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev, int comp_vector); int (*query_port)(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); int (*modify_port)(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); /** * The following mandatory functions are used only at device * registration. Keep functions such as these at the end of this * structure to avoid cache line misses when accessing struct ib_device * in fast paths. */ int (*get_port_immutable)(struct ib_device *device, u32 port_num, struct ib_port_immutable *immutable); enum rdma_link_layer (*get_link_layer)(struct ib_device *device, u32 port_num); /** * When calling get_netdev, the HW vendor's driver should return the * net device of device @device at port @port_num or NULL if such * a net device doesn't exist. The vendor driver should call dev_hold * on this net device. The HW vendor's device driver must guarantee * that this function returns NULL before the net device has finished * NETDEV_UNREGISTER state. */ struct net_device *(*get_netdev)(struct ib_device *device, u32 port_num); /** * rdma netdev operation * * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params * must return -EOPNOTSUPP if it doesn't support the specified type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int (*rdma_netdev_get_params)(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, struct rdma_netdev_alloc_params *params); /** * query_gid should be return GID value for @device, when @port_num * link layer is either IB or iWarp. It is no-op if @port_num port * is RoCE link layer. */ int (*query_gid)(struct ib_device *device, u32 port_num, int index, union ib_gid *gid); /** * When calling add_gid, the HW vendor's driver should add the gid * of device of port at gid index available at @attr. Meta-info of * that gid (for example, the network device related to this gid) is * available at @attr. @context allows the HW vendor driver to store * extra information together with a GID entry. The HW vendor driver may * allocate memory to contain this information and store it in @context * when a new GID entry is written to. Params are consistent until the * next call of add_gid or delete_gid. The function should return 0 on * success or error otherwise. The function could be called * concurrently for different ports. This function is only called when * roce_gid_table is used. */ int (*add_gid)(const struct ib_gid_attr *attr, void **context); /** * When calling del_gid, the HW vendor's driver should delete the * gid of device @device at gid index gid_index of port port_num * available in @attr. * Upon the deletion of a GID entry, the HW vendor must free any * allocated memory. The caller will clear @context afterwards. * This function is only called when roce_gid_table is used. */ int (*del_gid)(const struct ib_gid_attr *attr, void **context); int (*query_pkey)(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int (*alloc_ucontext)(struct ib_ucontext *context, struct ib_udata *udata); void (*dealloc_ucontext)(struct ib_ucontext *context); int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma); /** * This will be called once refcount of an entry in mmap_xa reaches * zero. The type of the memory that was mapped may differ between * entries and is opaque to the rdma_user_mmap interface. * Therefore needs to be implemented by the driver in mmap_free. */ void (*mmap_free)(struct rdma_user_mmap_entry *entry); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); int (*alloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*dealloc_pd)(struct ib_pd *pd, struct ib_udata *udata); int (*create_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*create_user_ah)(struct ib_ah *ah, struct rdma_ah_init_attr *attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*destroy_ah)(struct ib_ah *ah, u32 flags); int (*create_srq)(struct ib_srq *srq, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); int (*destroy_srq)(struct ib_srq *srq, struct ib_udata *udata); int (*create_qp)(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata); int (*create_cq)(struct ib_cq *cq, const struct ib_cq_init_attr *attr, struct uverbs_attr_bundle *attrs); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*destroy_cq)(struct ib_cq *cq, struct ib_udata *udata); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_udata *udata); struct ib_mr *(*reg_user_mr_dmabuf)(struct ib_pd *pd, u64 offset, u64 length, u64 virt_addr, int fd, int mr_access_flags, struct uverbs_attr_bundle *attrs); struct ib_mr *(*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); int (*dereg_mr)(struct ib_mr *mr, struct ib_udata *udata); struct ib_mr *(*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *(*alloc_mr_integrity)(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); int (*advise_mr)(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge, struct uverbs_attr_bundle *attrs); /* * Kernel users should universally support relaxed ordering (RO), as * they are designed to read data only after observing the CQE and use * the DMA API correctly. * * Some drivers implicitly enable RO if platform supports it. */ int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); int (*alloc_mw)(struct ib_mw *mw, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*alloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); int (*dealloc_xrcd)(struct ib_xrcd *xrcd, struct ib_udata *udata); struct ib_flow *(*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); int (*destroy_flow_action)(struct ib_flow_action *action); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *ivf); int (*get_vf_stats)(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int (*get_vf_guid)(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*set_vf_guid)(struct ib_device *device, int vf, u32 port, u64 guid, int type); struct ib_wq *(*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); int (*destroy_wq)(struct ib_wq *wq, struct ib_udata *udata); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); int (*create_rwq_ind_table)(struct ib_rwq_ind_table *ib_rwq_ind_table, struct ib_rwq_ind_table_init_attr *init_attr, struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dm *(*alloc_dm)(struct ib_device *device, struct ib_ucontext *context, struct ib_dm_alloc_attr *attr, struct uverbs_attr_bundle *attrs); int (*dealloc_dm)(struct ib_dm *dm, struct uverbs_attr_bundle *attrs); struct ib_mr *(*reg_dm_mr)(struct ib_pd *pd, struct ib_dm *dm, struct ib_dm_mr_attr *attr, struct uverbs_attr_bundle *attrs); int (*create_counters)(struct ib_counters *counters, struct uverbs_attr_bundle *attrs); int (*destroy_counters)(struct ib_counters *counters); int (*read_counters)(struct ib_counters *counters, struct ib_counters_read_attr *counters_read_attr, struct uverbs_attr_bundle *attrs); int (*map_mr_sg_pi)(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset); /** * alloc_hw_[device,port]_stats - Allocate a struct rdma_hw_stats and * fill in the driver initialized data. The struct is kfree()'ed by * the sysfs core when the device is removed. A lifespan of -1 in the * return struct tells the core to set a default lifespan. */ struct rdma_hw_stats *(*alloc_hw_device_stats)(struct ib_device *device); struct rdma_hw_stats *(*alloc_hw_port_stats)(struct ib_device *device, u32 port_num); /** * get_hw_stats - Fill in the counter value(s) in the stats struct. * @index - The index in the value array we wish to have updated, or * num_counters if we want all stats updated * Return codes - * < 0 - Error, no counters updated * index - Updated the single counter pointed to by index * num_counters - Updated all counters (will reset the timestamp * and prevent further calls for lifespan milliseconds) * Drivers are allowed to update all counters in leiu of just the * one given in index at their option */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u32 port, int index); /** * modify_hw_stat - Modify the counter configuration * @enable: true/false when enable/disable a counter * Return codes - 0 on success or error code otherwise. */ int (*modify_hw_stat)(struct ib_device *device, u32 port, unsigned int counter_index, bool enable); /** * Allows rdma drivers to add their own restrack attributes. */ int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_mr_entry_raw)(struct sk_buff *msg, struct ib_mr *ibmr); int (*fill_res_cq_entry)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_cq_entry_raw)(struct sk_buff *msg, struct ib_cq *ibcq); int (*fill_res_qp_entry)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_qp_entry_raw)(struct sk_buff *msg, struct ib_qp *ibqp); int (*fill_res_cm_id_entry)(struct sk_buff *msg, struct rdma_cm_id *id); int (*fill_res_srq_entry)(struct sk_buff *msg, struct ib_srq *ib_srq); int (*fill_res_srq_entry_raw)(struct sk_buff *msg, struct ib_srq *ib_srq); /* Device lifecycle callbacks */ /* * Called after the device becomes registered, before clients are * attached */ int (*enable_driver)(struct ib_device *dev); /* * This is called as part of ib_dealloc_device(). */ void (*dealloc_driver)(struct ib_device *dev); /* iWarp CM callbacks */ void (*iw_add_ref)(struct ib_qp *qp); void (*iw_rem_ref)(struct ib_qp *qp); struct ib_qp *(*iw_get_qp)(struct ib_device *device, int qpn); int (*iw_connect)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_accept)(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param); int (*iw_reject)(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len); int (*iw_create_listen)(struct iw_cm_id *cm_id, int backlog); int (*iw_destroy_listen)(struct iw_cm_id *cm_id); /** * counter_bind_qp - Bind a QP to a counter. * @counter - The counter to be bound. If counter->id is zero then * the driver needs to allocate a new counter and set counter->id */ int (*counter_bind_qp)(struct rdma_counter *counter, struct ib_qp *qp); /** * counter_unbind_qp - Unbind the qp from the dynamically-allocated * counter and bind it onto the default one */ int (*counter_unbind_qp)(struct ib_qp *qp); /** * counter_dealloc -De-allocate the hw counter */ int (*counter_dealloc)(struct rdma_counter *counter); /** * counter_alloc_stats - Allocate a struct rdma_hw_stats and fill in * the driver initialized data. */ struct rdma_hw_stats *(*counter_alloc_stats)( struct rdma_counter *counter); /** * counter_update_stats - Query the stats value of this counter */ int (*counter_update_stats)(struct rdma_counter *counter); /** * Allows rdma drivers to add their own restrack attributes * dumped via 'rdma stat' iproute2 command. */ int (*fill_stat_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr); /* query driver for its ucontext properties */ int (*query_ucontext)(struct ib_ucontext *context, struct uverbs_attr_bundle *attrs); /* * Provide NUMA node. This API exists for rdmavt/hfi1 only. * Everyone else relies on Linux memory management model. */ int (*get_numa_node)(struct ib_device *dev); /** * add_sub_dev - Add a sub IB device */ struct ib_device *(*add_sub_dev)(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** * del_sub_dev - Delete a sub IB device */ void (*del_sub_dev)(struct ib_device *sub_dev); /** * ufile_cleanup - Attempt to cleanup ubojects HW resources inside * the ufile. */ void (*ufile_hw_cleanup)(struct ib_uverbs_file *ufile); /** * report_port_event - Drivers need to implement this if they have * some private stuff to handle when link status changes. */ void (*report_port_event)(struct ib_device *ibdev, struct net_device *ndev, unsigned long event); DECLARE_RDMA_OBJ_SIZE(ib_ah); DECLARE_RDMA_OBJ_SIZE(ib_counters); DECLARE_RDMA_OBJ_SIZE(ib_cq); DECLARE_RDMA_OBJ_SIZE(ib_mw); DECLARE_RDMA_OBJ_SIZE(ib_pd); DECLARE_RDMA_OBJ_SIZE(ib_qp); DECLARE_RDMA_OBJ_SIZE(ib_rwq_ind_table); DECLARE_RDMA_OBJ_SIZE(ib_srq); DECLARE_RDMA_OBJ_SIZE(ib_ucontext); DECLARE_RDMA_OBJ_SIZE(ib_xrcd); }; struct ib_core_device { /* device must be the first element in structure until, * union of ib_core_device and device exists in ib_device. */ struct device dev; possible_net_t rdma_net; struct kobject *ports_kobj; struct list_head port_list; struct ib_device *owner; /* reach back to owner ib_device */ }; struct rdma_restrack_root; struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; struct ib_device_ops ops; char name[IB_DEVICE_NAME_MAX]; struct rcu_head rcu_head; struct list_head event_handler_list; /* Protects event_handler_list */ struct rw_semaphore event_handler_rwsem; /* Protects QP's event_handler calls and open_qp list */ spinlock_t qp_open_list_lock; struct rw_semaphore client_data_rwsem; struct xarray client_data; struct mutex unregistration_lock; /* Synchronize GID, Pkey cache entries, subnet prefix, LMC */ rwlock_t cache_lock; /** * port_data is indexed by port number */ struct ib_port_data *port_data; int num_comp_vectors; union { struct device dev; struct ib_core_device coredev; }; /* First group is for device attributes, * Second group is for driver provided attributes (optional). * Third group is for the hw_stats * It is a NULL terminated array. */ const struct attribute_group *groups[4]; u64 uverbs_cmd_mask; char node_desc[IB_DEVICE_NODE_DESC_MAX]; __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; /* Indicates kernel verbs support, should not be used in drivers */ u16 kverbs_provider:1; /* CQ adaptive moderation (RDMA DIM) */ u16 use_cq_dim:1; u8 node_type; u32 phys_port_cnt; struct ib_device_attr attrs; struct hw_stats_device_data *hw_stats_data; #ifdef CONFIG_CGROUP_RDMA struct rdmacg_device cg_device; #endif u32 index; spinlock_t cq_pools_lock; struct list_head cq_pools[IB_POLL_LAST_POOL_TYPE + 1]; struct rdma_restrack_root *res; const struct uapi_definition *driver_def; /* * Positive refcount indicates that the device is currently * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; struct work_struct unregistration_work; const struct rdma_link_ops *link_ops; /* Protects compat_devs xarray modifications */ struct mutex compat_devs_mutex; /* Maintains compat devices for each net namespace */ struct xarray compat_devs; /* Used by iWarp CM */ char iw_ifname[IFNAMSIZ]; u32 iw_driver_flags; u32 lag_flags; /* A parent device has a list of sub-devices */ struct mutex subdev_lock; struct list_head subdev_list_head; /* A sub device has a type and a parent */ enum rdma_nl_dev_type type; struct ib_device *parent; struct list_head subdev_list; enum rdma_nl_name_assign_type name_assign_type; }; static inline void *rdma_zalloc_obj(struct ib_device *dev, size_t size, gfp_t gfp, bool is_numa_aware) { if (is_numa_aware && dev->ops.get_numa_node) return kzalloc_node(size, gfp, dev->ops.get_numa_node(dev)); return kzalloc(size, gfp); } struct ib_client_nl_info; struct ib_client { const char *name; int (*add)(struct ib_device *ibdev); void (*remove)(struct ib_device *, void *client_data); void (*rename)(struct ib_device *dev, void *client_data); int (*get_nl_info)(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res); int (*get_global_nl_info)(struct ib_client_nl_info *res); /* Returns the net_dev belonging to this ib_client and matching the * given parameters. * @dev: An RDMA device that the net_dev use for communication. * @port: A physical port number on the RDMA device. * @pkey: P_Key that the net_dev uses if applicable. * @gid: A GID that the net_dev uses to communicate. * @addr: An IP address the net_dev is configured with. * @client_data: The device's client data set by ib_set_client_data(). * * An ib_client that implements a net_dev on top of RDMA devices * (such as IP over IB) should implement this callback, allowing the * rdma_cm module to find the right net_dev for a given request. * * The caller is responsible for calling dev_put on the returned * netdev. */ struct net_device *(*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); refcount_t uses; struct completion uses_zero; u32 client_id; /* kverbs are not required by the client */ u8 no_kverbs_req:1; }; /* * IB block DMA iterator * * Iterates the DMA-mapped SGL in contiguous memory blocks aligned * to a HW supported page size. */ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ }; struct ib_device *_ib_alloc_device(size_t size); #define ib_alloc_device(drv_struct, member) \ container_of(_ib_alloc_device(sizeof(struct drv_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ struct drv_struct, member))), \ struct drv_struct, member) void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); int ib_register_device(struct ib_device *device, const char *name, struct device *dma_device); void ib_unregister_device(struct ib_device *device); void ib_unregister_driver(enum rdma_driver_id driver_id); void ib_unregister_device_and_put(struct ib_device *device); void ib_unregister_device_queued(struct ib_device *ib_dev); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); void __rdma_block_iter_start(struct ib_block_iter *biter, struct scatterlist *sglist, unsigned int nents, unsigned long pgsz); bool __rdma_block_iter_next(struct ib_block_iter *biter); /** * rdma_block_iter_dma_address - get the aligned dma address of the current * block held by the block iterator. * @biter: block iterator holding the memory block */ static inline dma_addr_t rdma_block_iter_dma_address(struct ib_block_iter *biter) { return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1); } /** * rdma_for_each_block - iterate over contiguous memory blocks of the sg list * @sglist: sglist to iterate over * @biter: block iterator holding the memory block * @nents: maximum number of sg entries to iterate over * @pgsz: best HW supported page size to use * * Callers may use rdma_block_iter_dma_address() to get each * blocks aligned DMA address. */ #define rdma_for_each_block(sglist, biter, nents, pgsz) \ for (__rdma_block_iter_start(biter, sglist, nents, \ pgsz); \ __rdma_block_iter_next(biter);) /** * ib_get_client_data - Get IB client context * @device:Device to get context for * @client:Client to get context for * * ib_get_client_data() returns the client context data set with * ib_set_client_data(). This can only be called while the client is * registered to the device, once the ib_client remove() callback returns this * cannot be called. */ static inline void *ib_get_client_data(struct ib_device *device, struct ib_client *client) { return xa_load(&device->client_data, client->client_id); } void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); void ib_set_device_ops(struct ib_device *device, const struct ib_device_ops *ops); int rdma_user_mmap_io(struct ib_ucontext *ucontext, struct vm_area_struct *vma, unsigned long pfn, unsigned long size, pgprot_t prot, struct rdma_user_mmap_entry *entry); int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length); int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 min_pgoff, u32 max_pgoff); #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS) void rdma_user_mmap_disassociate(struct ib_device *device); #else static inline void rdma_user_mmap_disassociate(struct ib_device *device) { } #endif static inline int rdma_user_mmap_entry_insert_exact(struct ib_ucontext *ucontext, struct rdma_user_mmap_entry *entry, size_t length, u32 pgoff) { return rdma_user_mmap_entry_insert_range(ucontext, entry, length, pgoff, pgoff); } struct rdma_user_mmap_entry * rdma_user_mmap_entry_get_pgoff(struct ib_ucontext *ucontext, unsigned long pgoff); struct rdma_user_mmap_entry * rdma_user_mmap_entry_get(struct ib_ucontext *ucontext, struct vm_area_struct *vma); void rdma_user_mmap_entry_put(struct rdma_user_mmap_entry *entry); void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry); static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len) { return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0; } static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } static inline bool ib_is_buffer_cleared(const void __user *p, size_t len) { bool ret; u8 *buf; if (len > USHRT_MAX) return false; buf = memdup_user(p, len); if (IS_ERR(buf)) return false; ret = !memchr_inv(buf, 0, len); kfree(buf); return ret; } static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t offset, size_t len) { return ib_is_buffer_cleared(udata->inbuf + offset, len); } /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for * the given QP state transition. * @cur_state: Current QP state * @next_state: Next QP state * @type: QP type * @mask: Mask of supplied QP attributes * * This function is a helper function that a low-level driver's * modify_qp method can use to validate the consumer's input. It * checks that cur_state and next_state are valid QP states, that a * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(const struct ib_event *event); int ib_query_port(struct ib_device *device, u32 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u32 port_num); /** * rdma_cap_ib_switch - Check if the device is IB switch * @device: Device to check * * Device driver is responsible for setting is_switch bit on * in ib_device structure at init time. * * Return: true if the device is IB switch. */ static inline bool rdma_cap_ib_switch(const struct ib_device *device) { return device->is_switch; } /** * rdma_start_port - Return the first valid port number for the device * specified * * @device: Device to be checked * * Return start port number */ static inline u32 rdma_start_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : 1; } /** * rdma_for_each_port - Iterate over all valid port numbers of the IB device * @device - The struct ib_device * to iterate over * @iter - The unsigned int to store the port number */ #define rdma_for_each_port(device, iter) \ for (iter = rdma_start_port(device + \ BUILD_BUG_ON_ZERO(!__same_type(u32, \ iter))); \ iter <= rdma_end_port(device); iter++) /** * rdma_end_port - Return the last valid port number for the device * specified * * @device: Device to be checked * * Return last port number */ static inline u32 rdma_end_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline int rdma_is_port_valid(const struct ib_device *device, unsigned int port) { return (port >= rdma_start_port(device) && port <= rdma_end_port(device)); } static inline bool rdma_is_grh_required(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_IB_GRH_REQUIRED; } static inline bool rdma_protocol_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IB; } static inline bool rdma_protocol_roce(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); } static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; } static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } static inline bool rdma_protocol_iwarp(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; } static inline bool rdma_ib_or_roce(const struct ib_device *device, u32 port_num) { return rdma_protocol_ib(device, port_num) || rdma_protocol_roce(device, port_num); } static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET; } static inline bool rdma_protocol_usnic(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_PROT_USNIC; } /** * rdma_cap_ib_mad - Check if the port of a device supports Infiniband * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Management Datagrams (MAD) are a required part of the InfiniBand * specification and are supported on all InfiniBand devices. A slightly * extended version are also supported on OPA interfaces. * * Return: true if the port supports sending/receiving of MAD packets. */ static inline bool rdma_cap_ib_mad(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_MAD; } /** * rdma_cap_opa_mad - Check if the port of device provides support for OPA * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Intel OmniPath devices extend and/or replace the InfiniBand Management * datagrams with their own versions. These OPA MADs share many but not all of * the characteristics of InfiniBand MADs. * * OPA MADs differ in the following ways: * * 1) MADs are variable size up to 2K * IBTA defined MADs remain fixed at 256 bytes * 2) OPA SMPs must carry valid PKeys * 3) OPA SMP packets are a different format * * Return: true if the port supports OPA MAD packet formats. */ static inline bool rdma_cap_opa_mad(struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_MAD; } /** * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). * @device: Device to check * @port_num: Port number to check * * Each InfiniBand node is required to provide a Subnet Management Agent * that the subnet manager can access. Prior to the fabric being fully * configured by the subnet manager, the SMA is accessed via a well known * interface called the Subnet Management Interface (SMI). This interface * uses directed route packets to communicate with the SM to get around the * chicken and egg problem of the SM needing to know what's on the fabric * in order to configure the fabric, and needing to configure the fabric in * order to send packets to the devices on the fabric. These directed * route packets do not need the fabric fully configured in order to reach * their destination. The SMI is the only method allowed to send * directed route packets on an InfiniBand fabric. * * Return: true if the port provides an SMI. */ static inline bool rdma_cap_ib_smi(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SMI; } /** * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband * Communication Manager. * @device: Device to check * @port_num: Port number to check * * The InfiniBand Communication Manager is one of many pre-defined General * Service Agents (GSA) that are accessed via the General Service * Interface (GSI). It's role is to facilitate establishment of connections * between nodes as well as other management related tasks for established * connections. * * Return: true if the port supports an IB CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_ib_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_CM; } /** * rdma_cap_iw_cm - Check if the port of device has the capability IWARP * Communication Manager. * @device: Device to check * @port_num: Port number to check * * Similar to above, but specific to iWARP connections which have a different * managment protocol than InfiniBand. * * Return: true if the port supports an iWARP CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_iw_cm(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IW_CM; } /** * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband * Subnet Administration. * @device: Device to check * @port_num: Port number to check * * An InfiniBand Subnet Administration (SA) service is a pre-defined General * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand * fabrics, devices should resolve routes to other hosts by contacting the * SA to query the proper route. * * Return: true if the port should act as a client to the fabric Subnet * Administration interface. This does not imply that the SA service is * running locally. */ static inline bool rdma_cap_ib_sa(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_IB_SA; } /** * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband * Multicast. * @device: Device to check * @port_num: Port number to check * * InfiniBand multicast registration is more complex than normal IPv4 or * IPv6 multicast registration. Each Host Channel Adapter must register * with the Subnet Manager when it wishes to join a multicast group. It * should do so only once regardless of how many queue pairs it subscribes * to this group. And it should leave the group only after all queue pairs * attached to the group have been detached. * * Return: true if the port must undertake the additional adminstrative * overhead of registering/unregistering with the SM and tracking of the * total number of queue pairs attached to the multicast group. */ static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u32 port_num) { return rdma_cap_ib_sa(device, port_num); } /** * rdma_cap_af_ib - Check if the port of device has the capability * Native Infiniband Address. * @device: Device to check * @port_num: Port number to check * * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default * GID. RoCE uses a different mechanism, but still generates a GID via * a prescribed mechanism and port specific data. * * Return: true if the port uses a GID address to identify devices on the * network. */ static inline bool rdma_cap_af_ib(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_AF_IB; } /** * rdma_cap_eth_ah - Check if the port of device has the capability * Ethernet Address Handle. * @device: Device to check * @port_num: Port number to check * * RoCE is InfiniBand over Ethernet, and it uses a well defined technique * to fabricate GIDs over Ethernet/IP specific addresses native to the * port. Normally, packet headers are generated by the sending host * adapter, but when sending connectionless datagrams, we must manually * inject the proper headers for the fabric we are communicating over. * * Return: true if we are running as a RoCE port and must force the * addition of a Global Route Header built from our Ethernet Address * Handle into our header list for connectionless packets. */ static inline bool rdma_cap_eth_ah(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_ETH_AH; } /** * rdma_cap_opa_ah - Check if the port of device supports * OPA Address handles * @device: Device to check * @port_num: Port number to check * * Return: true if we are running on an OPA device which supports * the extended OPA addressing. */ static inline bool rdma_cap_opa_ah(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH; } /** * rdma_max_mad_size - Return the max MAD size required by this RDMA Port. * * @device: Device * @port_num: Port number * * This MAD size includes the MAD headers and MAD payload. No other headers * are included. * * Return the max MAD size required by the Port. Will return 0 if the port * does not support MADs */ static inline size_t rdma_max_mad_size(const struct ib_device *device, u32 port_num) { return device->port_data[port_num].immutable.max_mad_size; } /** * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table * @device: Device to check * @port_num: Port number to check * * RoCE GID table mechanism manages the various GIDs for a device. * * NOTE: if allocating the port's GID table has failed, this call will still * return true, but any RoCE GID table API will fail. * * Return: true if the port uses RoCE GID table mechanism in order to manage * its GIDs. */ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, u32 port_num) { return rdma_protocol_roce(device, port_num) && device->ops.add_gid && device->ops.del_gid; } /* * Check if the device supports READ W/ INVALIDATE. */ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) { /* * iWarp drivers must support READ W/ INVALIDATE. No other protocol * has support for it yet. */ return rdma_protocol_iwarp(dev, port_num); } /** * rdma_core_cap_opa_port - Return whether the RDMA Port is OPA or not. * @device: Device * @port_num: 1 based Port number * * Return true if port is an Intel OPA port , false if not */ static inline bool rdma_core_cap_opa_port(struct ib_device *device, u32 port_num) { return (device->port_data[port_num].immutable.core_cap_flags & RDMA_CORE_PORT_INTEL_OPA) == RDMA_CORE_PORT_INTEL_OPA; } /** * rdma_mtu_enum_to_int - Return the mtu of the port as an integer value. * @device: Device * @port_num: Port number * @mtu: enum value of MTU * * Return the MTU size supported by the port as an integer value. Will return * -1 if enum value of mtu is not supported. */ static inline int rdma_mtu_enum_to_int(struct ib_device *device, u32 port, int mtu) { if (rdma_core_cap_opa_port(device, port)) return opa_mtu_enum_to_int((enum opa_mtu)mtu); else return ib_mtu_enum_to_int((enum ib_mtu)mtu); } /** * rdma_mtu_from_attr - Return the mtu of the port from the port attribute. * @device: Device * @port_num: Port number * @attr: port attribute * * Return the MTU size supported by the port as an integer value. */ static inline int rdma_mtu_from_attr(struct ib_device *device, u32 port, struct ib_port_attr *attr) { if (rdma_core_cap_opa_port(device, port)) return attr->phys_mtu; else return ib_mtu_enum_to_int(attr->max_mtu); } int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *info); int ib_get_vf_stats(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats); int ib_get_vf_guid(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid, int type); int ib_query_pkey(struct ib_device *device, u32 port_num, u16 index, u16 *pkey); int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int ib_modify_port(struct ib_device *device, u32 port_num, int port_modify_mask, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, u32 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u32 port_num, u16 pkey, u16 *index); enum ib_pd_flags { /* * Create a memory registration for all memory in the system and place * the rkey for it into pd->unsafe_global_rkey. This can be used by * ULPs to avoid the overhead of dynamic MRs. * * This flag is generally considered unsafe and must only be used in * extremly trusted environments. Every use of it will log a warning * in the kernel log. */ IB_PD_UNSAFE_GLOBAL_RKEY = 0x01, }; struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); /** * ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. * @flags: protection domain flags * * A protection domain object provides an association between QPs, shared * receive queues, address handles, memory regions, and memory windows. * * Every PD has a local_dma_lkey which can be used as the lkey value for local * memory operations. */ #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), KBUILD_MODNAME) int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata); /** * ib_dealloc_pd - Deallocate kernel PD * @pd: The protection domain * * NOTE: for user PD use ib_dealloc_pd_user with valid udata! */ static inline void ib_dealloc_pd(struct ib_pd *pd) { int ret = ib_dealloc_pd_user(pd, NULL); WARN_ONCE(ret, "Destroy of kernel PD shouldn't fail"); } enum rdma_create_ah_flags { /* In a sleepable context */ RDMA_CREATE_AH_SLEEPABLE = BIT(0), }; /** * rdma_create_ah - Creates an address handle for the given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @flags: Create address handle flags (see enum rdma_create_ah_flags). * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags); /** * rdma_create_user_ah - Creates an address handle for the given address vector. * It resolves destination mac address for ah attribute of RoCE type. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @udata: pointer to user's input output buffer information need by * provider driver. * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata); /** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse * @net_type: type of header to parse * @sgid: place to store source gid * @dgid: place to store destination gid */ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid); /** * ib_get_rdma_header_version - Get the header version * @hdr: the L3 header to parse */ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** * ib_init_ah_attr_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. * @wc: Work completion associated with the received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. * When ib_init_ah_attr_from_wc() returns success, * (a) for IB link layer it optionally contains a reference to SGID attribute * when GRH is present for IB link layer. * (b) for RoCE link layer it contains a reference to SGID attribute. * User must invoke rdma_cleanup_ah_attr_gid_attr() to release reference to SGID * attributes which are initialized using ib_init_ah_attr_from_wc(). * */ int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. * @wc: Work completion information associated with a received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @port_num: The outbound port number to associate with the address. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u32 port_num); /** * rdma_modify_ah - Modifies the address vector associated with an address * handle. * @ah: The address handle to modify. * @ah_attr: The new address vector attributes to associate with the * address handle. */ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_query_ah - Queries the address vector associated with an address * handle. * @ah: The address handle to query. * @ah_attr: The address vector attributes associated with the address * handle. */ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); enum rdma_destroy_ah_flags { /* In a sleepable context */ RDMA_DESTROY_AH_SLEEPABLE = BIT(0), }; /** * rdma_destroy_ah_user - Destroys an address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * @udata: Valid user data or NULL for kernel objects */ int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata); /** * rdma_destroy_ah - Destroys an kernel address handle. * @ah: The address handle to destroy. * @flags: Destroy address handle flags (see enum rdma_destroy_ah_flags). * * NOTE: for user ah use rdma_destroy_ah_user with valid udata! */ static inline void rdma_destroy_ah(struct ib_ah *ah, u32 flags) { int ret = rdma_destroy_ah_user(ah, flags, NULL); WARN_ONCE(ret, "Destroy of kernel AH shouldn't fail"); } struct ib_srq *ib_create_srq_user(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_usrq_object *uobject, struct ib_udata *udata); static inline struct ib_srq * ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr) { if (!pd->device->ops.create_srq) return ERR_PTR(-EOPNOTSUPP); return ib_create_srq_user(pd, srq_init_attr, NULL, NULL); } /** * ib_modify_srq - Modifies the attributes for the specified SRQ. * @srq: The SRQ to modify. * @srq_attr: On input, specifies the SRQ attributes to modify. On output, * the current values of selected SRQ attributes are returned. * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ * are being modified. * * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or * IB_SRQ_LIMIT to set the SRQ's limit and request notification when * the number of receives queued drops below the limit. */ int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask); /** * ib_query_srq - Returns the attribute list and current values for the * specified SRQ. * @srq: The SRQ to query. * @srq_attr: The attributes of the specified SRQ. */ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); /** * ib_destroy_srq_user - Destroys the specified SRQ. * @srq: The SRQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata); /** * ib_destroy_srq - Destroys the specified kernel SRQ. * @srq: The SRQ to destroy. * * NOTE: for user srq use ib_destroy_srq_user with valid udata! */ static inline void ib_destroy_srq(struct ib_srq *srq) { int ret = ib_destroy_srq_user(srq, NULL); WARN_ONCE(ret, "Destroy of kernel SRQ shouldn't fail"); } /** * ib_post_srq_recv - Posts a list of work requests to the specified SRQ. * @srq: The SRQ to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_srq_recv(struct ib_srq *srq, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return srq->device->ops.post_srq_recv(srq, recv_wr, bad_recv_wr ? : &dummy); } struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, const char *caller); /** * ib_create_qp - Creates a kernel QP associated with the specific protection * domain. * @pd: The protection domain associated with the QP. * @init_attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. */ static inline struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *init_attr) { return ib_create_qp_kernel(pd, init_attr, KBUILD_MODNAME); } /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); /** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. * @qp_attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @qp_attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. */ int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask); /** * ib_query_qp - Returns the attribute list and current values for the * specified QP. * @qp: The QP to query. * @qp_attr: The attributes of the specified QP. * @qp_attr_mask: A bit-mask used to select specific attributes to query. * @qp_init_attr: Additional attributes of the selected QP. * * The qp_attr_mask may be used to limit the query to gathering only the * selected attributes. */ int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); /** * ib_destroy_qp - Destroys the specified QP. * @qp: The QP to destroy. * @udata: Valid udata or NULL for kernel objects */ int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata); /** * ib_destroy_qp - Destroys the specified kernel QP. * @qp: The QP to destroy. * * NOTE: for user qp use ib_destroy_qp_user with valid udata! */ static inline int ib_destroy_qp(struct ib_qp *qp) { return ib_destroy_qp_user(qp, NULL); } /** * ib_open_qp - Obtain a reference to an existing sharable QP. * @xrcd - XRC domain * @qp_open_attr: Attributes identifying the QP to open. * * Returns a reference to a sharable QP. */ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr); /** * ib_close_qp - Release an external reference to a QP. * @qp: The QP handle to release * * The opened QP handle is released by the caller. The underlying * shared QP is not destroyed until all internal references are released. */ int ib_close_qp(struct ib_qp *qp); /** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. * * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate * error is returned, the QP state shall not be affected, * ib_post_send() will return an immediate error after queueing any * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, const struct ib_send_wr *send_wr, const struct ib_send_wr **bad_send_wr) { const struct ib_send_wr *dummy; return qp->device->ops.post_send(qp, send_wr, bad_send_wr ? : &dummy); } /** * ib_post_recv - Posts a list of work requests to the receive queue of * the specified QP. * @qp: The QP to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr) { const struct ib_recv_wr *dummy; return qp->device->ops.post_recv(qp, recv_wr, bad_recv_wr ? : &dummy); } struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, const char *caller); static inline struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx) { return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx, KBUILD_MODNAME); } struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx, const char *caller); /** * ib_alloc_cq_any: Allocate kernel CQ * @dev: The IB device * @private: Private data attached to the CQE * @nr_cqe: Number of CQEs in the CQ * @poll_ctx: Context used for polling the CQ */ static inline struct ib_cq *ib_alloc_cq_any(struct ib_device *dev, void *private, int nr_cqe, enum ib_poll_context poll_ctx) { return __ib_alloc_cq_any(dev, private, nr_cqe, poll_ctx, KBUILD_MODNAME); } void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. * @comp_handler: A user-specified callback that is invoked when a * completion event occurs on the CQ. * @event_handler: A user-specified callback that is invoked when an * asynchronous event not associated with a completion occurs on the CQ. * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cq_attr: The attributes the CQ should be created upon. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *__ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr, const char *caller); #define ib_create_cq(device, cmp_hndlr, evt_hndlr, cq_ctxt, cq_attr) \ __ib_create_cq((device), (cmp_hndlr), (evt_hndlr), (cq_ctxt), (cq_attr), KBUILD_MODNAME) /** * ib_resize_cq - Modifies the capacity of the CQ. * @cq: The CQ to resize. * @cqe: The minimum size of the CQ. * * Users can examine the cq structure to determine the actual CQ size. */ int ib_resize_cq(struct ib_cq *cq, int cqe); /** * rdma_set_cq_moderation - Modifies moderation params of the CQ * @cq: The CQ to modify. * @cq_count: number of CQEs that will trigger an event * @cq_period: max period of time in usec before triggering an event * */ int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq_user - Destroys the specified CQ. * @cq: The CQ to destroy. * @udata: Valid user data or NULL for kernel objects */ int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata); /** * ib_destroy_cq - Destroys the specified kernel CQ. * @cq: The CQ to destroy. * * NOTE: for user cq use ib_destroy_cq_user with valid udata! */ static inline void ib_destroy_cq(struct ib_cq *cq) { int ret = ib_destroy_cq_user(cq, NULL); WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail"); } /** * ib_poll_cq - poll a CQ for completion(s) * @cq:the CQ being polled * @num_entries:maximum number of completions to return * @wc:array of at least @num_entries &struct ib_wc where completions * will be returned * * Poll a CQ for (possibly multiple) completions. If the return value * is < 0, an error occurred. If the return value is >= 0, it is the * number of completions returned. If the return value is * non-negative and < num_entries, then the CQ was emptied. */ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { return cq->device->ops.poll_cq(cq, num_entries, wc); } /** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP * to request an event on the next solicited event or next work * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS * may also be |ed in to request a hint about missed events, as * described below. * * Return Value: * < 0 means an error occurred while requesting notification * == 0 means notification was requested successfully, and if * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events * were missed and it is safe to wait for another event. In * this case is it guaranteed that any work completions added * to the CQ since the last CQ poll will trigger a completion * notification event. * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed * in. It means that the consumer must poll the CQ again to * make sure it is empty to avoid missing an event because of a * race between requesting notification and an entry being * added to the CQ. This return value means it is possible * (but not guaranteed) that a work completion has been added * to the CQ since the last poll without triggering a * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags) { return cq->device->ops.req_notify_cq(cq, flags); } struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe, int comp_vector_hint, enum ib_poll_context poll_ctx); void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe); /* * Drivers that don't need a DMA mapping at the RDMA layer, set dma_device to * NULL. This causes the ib_dma* helpers to just stash the kernel virtual * address into the dma address. */ static inline bool ib_uses_virt_dma(struct ib_device *dev) { return IS_ENABLED(CONFIG_INFINIBAND_VIRT_DMA) && !dev->dma_device; } /* * Check if a IB device's underlying DMA mapping supports P2PDMA transfers. */ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return false; return dma_pci_p2pdma_supported(dev->dma_device); } /** * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after * going through the dma_addr marshalling. */ static inline void *ib_virt_dma_to_ptr(u64 dma_addr) { /* virt_dma mode maps the kvs's directly into the dma addr */ return (void *)(uintptr_t)dma_addr; } /** * ib_virt_dma_to_page - Convert a dma_addr to a struct page * @dma_addr: The DMA address * * Used by ib_uses_virt_dma() device to get back to the struct page after going * through the dma_addr marshalling. */ static inline struct page *ib_virt_dma_to_page(u64 dma_addr) { return virt_to_page(ib_virt_dma_to_ptr(dma_addr)); } /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created * @dma_addr: The DMA address to check */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { if (ib_uses_virt_dma(dev)) return 0; return dma_mapping_error(dev->dma_device, dma_addr); } /** * ib_dma_map_single - Map a kernel virtual address to DMA address * @dev: The device for which the dma_addr is to be created * @cpu_addr: The kernel virtual address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)cpu_addr; return dma_map_single(dev->dma_device, cpu_addr, size, direction); } /** * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_single(dev->dma_device, addr, size, direction); } /** * ib_dma_map_page - Map a physical page to DMA address * @dev: The device for which the dma_addr is to be created * @page: The page to be mapped * @offset: The offset within the page * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_page(struct ib_device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) { if (ib_uses_virt_dma(dev)) return (uintptr_t)(page_address(page) + offset); return dma_map_page(dev->dma_device, page, offset, size, direction); } /** * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { if (!ib_uses_virt_dma(dev)) dma_unmap_page(dev->dma_device, addr, size, direction); } int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents); static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (ib_uses_virt_dma(dev)) return ib_dma_virt_map_sg(dev, sg, nents); return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_dma_map_sgtable_attrs - Map a scatter/gather table to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The sg_table object describing the buffer * @direction: The direction of the DMA * @attrs: Optional DMA attributes for the map operation */ static inline int ib_dma_map_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { int nents; if (ib_uses_virt_dma(dev)) { nents = ib_dma_virt_map_sg(dev, sgt->sgl, sgt->orig_nents); if (!nents) return -EIO; sgt->nents = nents; return 0; } return dma_map_sgtable(dev->dma_device, sgt, direction, dma_attrs); } static inline void ib_dma_unmap_sgtable_attrs(struct ib_device *dev, struct sg_table *sgt, enum dma_data_direction direction, unsigned long dma_attrs) { if (!ib_uses_virt_dma(dev)) dma_unmap_sgtable(dev->dma_device, sgt, direction, dma_attrs); } /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { return ib_dma_map_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses * @dev: The device for which the DMA addresses were created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { ib_dma_unmap_sg_attrs(dev, sg, nents, direction, 0); } /** * ib_dma_max_seg_size - Return the size limit of a single DMA transfer * @dev: The device to query * * The returned value represents a size in bytes. */ static inline unsigned int ib_dma_max_seg_size(struct ib_device *dev) { if (ib_uses_virt_dma(dev)) return UINT_MAX; return dma_get_max_seg_size(dev->dma_device); } /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); } /** * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { if (!ib_uses_virt_dma(dev)) dma_sync_single_for_device(dev->dma_device, addr, size, dir); } /* ib_reg_user_mr - register a memory region for virtual addresses from kernel * space. This function should be called when 'current' is the owning MM. */ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags); /* ib_advise_mr - give an advice about an address range in a memory region */ int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge); /** * ib_dereg_mr_user - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * @udata: Valid user data or NULL for kernel object * * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata); /** * ib_dereg_mr - Deregisters a kernel memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * * This function can fail, if the memory region has memory windows bound to it. * * NOTE: for user mr use ib_dereg_mr_user with valid udata! */ static inline int ib_dereg_mr(struct ib_mr *mr) { return ib_dereg_mr_user(mr, NULL); } struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg); /** * ib_update_fast_reg_key - updates the key portion of the fast_reg MR * R_Key and L_Key. * @mr - struct ib_mr pointer to be updated. * @newkey - new key to be used. */ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) { mr->lkey = (mr->lkey & 0xffffff00) | newkey; mr->rkey = (mr->rkey & 0xffffff00) | newkey; } /** * ib_inc_rkey - increments the key portion of the given rkey. Can be used * for calculating a new rkey for type 2 memory windows. * @rkey - the rkey to increment. */ static inline u32 ib_inc_rkey(u32 rkey) { const u32 mask = 0x000000ff; return ((rkey + 1) & mask) | (rkey & ~mask); } /** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. * * In order to send and receive multicast packets, subnet * administration must have created the multicast group and configured * the fabric appropriately. The port associated with the specified * QP must also be a member of the multicast group. */ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_detach_mcast - Detaches the specified QP from a multicast group. * @qp: QP to detach from the multicast group. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. */ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device, struct inode *inode, struct ib_udata *udata); int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata); static inline int ib_check_mr_access(struct ib_device *ib_dev, unsigned int flags) { u64 device_cap = ib_dev->attrs.device_cap_flags; /* * Local write permission is required if remote write or * remote atomic permission is also requested. */ if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && !(flags & IB_ACCESS_LOCAL_WRITE)) return -EINVAL; if (flags & ~IB_ACCESS_SUPPORTED) return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EOPNOTSUPP; if ((flags & IB_ACCESS_FLUSH_GLOBAL && !(device_cap & IB_DEVICE_FLUSH_GLOBAL)) || (flags & IB_ACCESS_FLUSH_PERSISTENT && !(device_cap & IB_DEVICE_FLUSH_PERSISTENT))) return -EOPNOTSUPP; return 0; } static inline bool ib_access_writable(int access_flags) { /* * We have writable memory backing the MR if any of the following * access flags are set. "Local write" and "remote write" obviously * require write access. "Remote atomic" can do things like fetch and * add, which will modify memory, and "MW bind" can change permissions * by binding a window. */ return access_flags & (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND); } /** * ib_check_mr_status: lightweight check of MR status. * This routine may provide status checks on a selected * ib_mr. first use is for signature status check. * * @mr: A memory region. * @check_mask: Bitmask of which checks to perform from * ib_mr_status_check enumeration. * @mr_status: The container of relevant status checks. * failed checks will be indicated in the status bitmask * and the relevant info shall be in the error item. */ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); /** * ib_device_try_get: Hold a registration lock * device: The device to lock * * A device under an active registration lock cannot become unregistered. It * is only possible to obtain a registration lock on a device that is fully * registered, otherwise this function returns false. * * The registration lock is only necessary for actions which require the * device to still be registered. Uses that only require the device pointer to * be valid should use get_device(&ibdev->dev) to hold the memory. * */ static inline bool ib_device_try_get(struct ib_device *dev) { return refcount_inc_not_zero(&dev->refcount); } void ib_device_put(struct ib_device *device); struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, enum rdma_driver_id driver_id); struct ib_device *ib_device_get_by_name(const char *name, enum rdma_driver_id driver_id); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev, unsigned int port); struct net_device *ib_device_get_netdev(struct ib_device *ib_dev, u32 port); int ib_query_netdev_port(struct ib_device *ibdev, struct net_device *ndev, u32 *port); static inline enum ib_port_state ib_get_curr_port_state(struct net_device *net_dev) { return (netif_running(net_dev) && netif_carrier_ok(net_dev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; } void ib_dispatch_port_state_event(struct ib_device *ibdev, struct net_device *ndev); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset, unsigned int page_size); static inline int ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { int n; n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_ROCE) return attr->roce.dmac; return NULL; } static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.dlid = (u16)dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.dlid = dlid; } static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.dlid; return 0; } static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl) { attr->sl = sl; } static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr) { return attr->sl; } static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr, u8 src_path_bits) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.src_path_bits = src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.src_path_bits = src_path_bits; } static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.src_path_bits; return 0; } static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr, bool make_grd) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.make_grd = make_grd; } static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.make_grd; return false; } static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u32 port_num) { attr->port_num = port_num; } static inline u32 rdma_ah_get_port_num(const struct rdma_ah_attr *attr) { return attr->port_num; } static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr, u8 static_rate) { attr->static_rate = static_rate; } static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr) { return attr->static_rate; } static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr, enum ib_ah_flags flag) { attr->ah_flags = flag; } static inline enum ib_ah_flags rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr) { return attr->ah_flags; } static inline const struct ib_global_route *rdma_ah_read_grh(const struct rdma_ah_attr *attr) { return &attr->grh; } /*To retrieve and modify the grh */ static inline struct ib_global_route *rdma_ah_retrieve_grh(struct rdma_ah_attr *attr) { return &attr->grh; } static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid)); } static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr, __be64 prefix) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.subnet_prefix = prefix; } static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr, __be64 if_id) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.interface_id = if_id; } static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 sgid_index, u8 hop_limit, u8 traffic_class) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); attr->ah_flags = IB_AH_GRH; if (dgid) grh->dgid = *dgid; grh->flow_label = flow_label; grh->sgid_index = sgid_index; grh->hop_limit = hop_limit; grh->traffic_class = traffic_class; grh->sgid_attr = NULL; } void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr); void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 hop_limit, u8 traffic_class, const struct ib_gid_attr *sgid_attr); void rdma_copy_ah_attr(struct rdma_ah_attr *dest, const struct rdma_ah_attr *src); void rdma_replace_ah_attr(struct rdma_ah_attr *old, const struct rdma_ah_attr *new); void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src); /** * rdma_ah_find_type - Return address handle type. * * @dev: Device to be checked * @port_num: Port number */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u32 port_num) { if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; if (rdma_protocol_ib(dev, port_num)) { if (rdma_cap_opa_ah(dev, port_num)) return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; } if (dev->type == RDMA_DEVICE_TYPE_SMI) return RDMA_AH_ATTR_TYPE_IB; return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** * ib_lid_cpu16 - Return lid in 16bit CPU encoding. * In the current implementation the only way to * get the 32bit lid is from other sources for OPA. * For IB, lids will always be 16bits so cast the * value accordingly. * * @lid: A 32bit LID */ static inline u16 ib_lid_cpu16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return (u16)lid; } /** * ib_lid_be16 - Return lid in 16bit BE encoding. * * @lid: A 32bit LID */ static inline __be16 ib_lid_be16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return cpu_to_be16((u16)lid); } /** * ib_get_vector_affinity - Get the affinity mappings of a given completion * vector * @device: the rdma device * @comp_vector: index of completion vector * * Returns NULL on failure, otherwise a corresponding cpu map of the * completion vector (returns all-cpus map if the device driver doesn't * implement get_vector_affinity). */ static inline const struct cpumask * ib_get_vector_affinity(struct ib_device *device, int comp_vector) { if (comp_vector < 0 || comp_vector >= device->num_comp_vectors || !device->ops.get_vector_affinity) return NULL; return device->ops.get_vector_affinity(device, comp_vector); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @device: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ibdev); void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port); void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev); struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile); int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs); struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); int rdma_init_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), struct net_device *netdev); /** * rdma_device_to_ibdev - Get ib_device pointer from device pointer * * @device: device pointer for which ib_device pointer to retrieve * * rdma_device_to_ibdev() retrieves ib_device pointer from device. * */ static inline struct ib_device *rdma_device_to_ibdev(struct device *device) { struct ib_core_device *coredev = container_of(device, struct ib_core_device, dev); return coredev->owner; } /** * ibdev_to_node - return the NUMA node for a given ib_device * @dev: device to get the NUMA node for. */ static inline int ibdev_to_node(struct ib_device *ibdev) { struct device *parent = ibdev->dev.parent; if (!parent) return NUMA_NO_NODE; return dev_to_node(parent); } /** * rdma_device_to_drv_device - Helper macro to reach back to driver's * ib_device holder structure from device pointer. * * NOTE: New drivers should not make use of this API; This API is only for * existing drivers who have exposed sysfs entries using * ops->device_group. */ #define rdma_device_to_drv_device(dev, drv_dev_struct, ibdev_member) \ container_of(rdma_device_to_ibdev(dev), drv_dev_struct, ibdev_member) bool rdma_dev_access_netns(const struct ib_device *device, const struct net *net); #define IB_ROCE_UDP_ENCAP_VALID_PORT_MIN (0xC000) #define IB_ROCE_UDP_ENCAP_VALID_PORT_MAX (0xFFFF) #define IB_GRH_FLOWLABEL_MASK (0x000FFFFF) /** * rdma_flow_label_to_udp_sport - generate a RoCE v2 UDP src port value based * on the flow_label * * This function will convert the 20 bit flow_label input to a valid RoCE v2 * UDP src port 14 bit value. All RoCE V2 drivers should use this same * convention. */ static inline u16 rdma_flow_label_to_udp_sport(u32 fl) { u32 fl_low = fl & 0x03fff, fl_high = fl & 0xFC000; fl_low ^= fl_high >> 14; return (u16)(fl_low | IB_ROCE_UDP_ENCAP_VALID_PORT_MIN); } /** * rdma_calc_flow_label - generate a RDMA symmetric flow label value based on * local and remote qpn values * * This function folded the multiplication results of two qpns, 24 bit each, * fields, and converts it to a 20 bit results. * * This function will create symmetric flow_label value based on the local * and remote qpn values. this will allow both the requester and responder * to calculate the same flow_label for a given connection. * * This helper function should be used by driver in case the upper layer * provide a zero flow_label value. This is to improve entropy of RDMA * traffic in the network. */ static inline u32 rdma_calc_flow_label(u32 lqpn, u32 rqpn) { u64 v = (u64)lqpn * rqpn; v ^= v >> 20; v ^= v >> 40; return (u32)(v & IB_GRH_FLOWLABEL_MASK); } /** * rdma_get_udp_sport - Calculate and set UDP source port based on the flow * label. If flow label is not defined in GRH then * calculate it based on lqpn/rqpn. * * @fl: flow label from GRH * @lqpn: local qp number * @rqpn: remote qp number */ static inline u16 rdma_get_udp_sport(u32 fl, u32 lqpn, u32 rqpn) { if (!fl) fl = rdma_calc_flow_label(lqpn, rqpn); return rdma_flow_label_to_udp_sport(fl); } const struct ib_port_immutable* ib_port_immutable_read(struct ib_device *dev, unsigned int port); /** ib_add_sub_device - Add a sub IB device on an existing one * * @parent: The IB device that needs to add a sub device * @type: The type of the new sub device * @name: The name of the new sub device * * * Return 0 on success, an error code otherwise */ int ib_add_sub_device(struct ib_device *parent, enum rdma_nl_dev_type type, const char *name); /** ib_del_sub_device_and_put - Delect an IB sub device while holding a 'get' * * @sub: The sub device that is going to be deleted * * Return 0 on success, an error code otherwise */ int ib_del_sub_device_and_put(struct ib_device *sub); static inline void ib_mark_name_assigned_by_user(struct ib_device *ibdev) { ibdev->name_assign_type = RDMA_NAME_ASSIGN_TYPE_USER; } #endif /* IB_VERBS_H */ |
| 244 245 245 245 245 245 245 248 248 247 248 248 248 245 5 245 245 245 245 245 245 245 245 248 245 245 245 245 245 245 245 248 248 248 248 248 248 245 245 26 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NETLINK Kernel-user communication protocol. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Patrick McHardy <kaber@trash.net> * * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith * added netlink_proto_exit * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> * use nlk_sk, as sk->protinfo is on a diet 8) * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> * - inc module use count of module that owns * the kernel socket in case userspace opens * socket of same protocol * - remove all module support, since netlink is * mandatory if CONFIG_NET=y these days */ #include <linux/module.h> #include <linux/bpf.h> #include <linux/capability.h> #include <linux/kernel.h> #include <linux/filter.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/un.h> #include <linux/fcntl.h> #include <linux/termios.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/security.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/bitops.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/audit.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> #include <linux/net_namespace.h> #include <linux/nospec.h> #include <linux/btf_ids.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/scm.h> #include <net/netlink.h> #define CREATE_TRACE_POINTS #include <trace/events/netlink.h> #include "af_netlink.h" #include "genetlink.h" struct listeners { struct rcu_head rcu; unsigned long masks[]; }; /* state bits */ #define NETLINK_S_CONGESTED 0x0 static inline int netlink_is_kernel(struct sock *sk) { return nlk_test_bit(KERNEL_SOCKET, sk); } struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { "nlk_cb_mutex-ROUTE", "nlk_cb_mutex-1", "nlk_cb_mutex-USERSOCK", "nlk_cb_mutex-FIREWALL", "nlk_cb_mutex-SOCK_DIAG", "nlk_cb_mutex-NFLOG", "nlk_cb_mutex-XFRM", "nlk_cb_mutex-SELINUX", "nlk_cb_mutex-ISCSI", "nlk_cb_mutex-AUDIT", "nlk_cb_mutex-FIB_LOOKUP", "nlk_cb_mutex-CONNECTOR", "nlk_cb_mutex-NETFILTER", "nlk_cb_mutex-IP6_FW", "nlk_cb_mutex-DNRTMSG", "nlk_cb_mutex-KOBJECT_UEVENT", "nlk_cb_mutex-GENERIC", "nlk_cb_mutex-17", "nlk_cb_mutex-SCSITRANSPORT", "nlk_cb_mutex-ECRYPTFS", "nlk_cb_mutex-RDMA", "nlk_cb_mutex-CRYPTO", "nlk_cb_mutex-SMC", "nlk_cb_mutex-23", "nlk_cb_mutex-24", "nlk_cb_mutex-25", "nlk_cb_mutex-26", "nlk_cb_mutex-27", "nlk_cb_mutex-28", "nlk_cb_mutex-29", "nlk_cb_mutex-30", "nlk_cb_mutex-31", "nlk_cb_mutex-MAX_LINKS" }; static int netlink_dump(struct sock *sk, bool lock_taken); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion * and removal are protected with per bucket lock while using RCU list * modification primitives and may run in parallel to RCU protected lookups. * Destruction of the Netlink socket may only occur *after* nl_table_lock has * been acquired * either during or after the socket has been removed from * the list and after an RCU grace period. */ DEFINE_RWLOCK(nl_table_lock); EXPORT_SYMBOL_GPL(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); static BLOCKING_NOTIFIER_HEAD(netlink_chain); static const struct rhashtable_params netlink_rhashtable_params; void do_trace_netlink_extack(const char *msg) { trace_netlink_extack(msg); } EXPORT_SYMBOL(do_trace_netlink_extack); static inline u32 netlink_group_mask(u32 group) { if (group > 32) return 0; return group ? 1 << (group - 1) : 0; } static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); if (new == NULL) return NULL; NETLINK_CB(new).portid = NETLINK_CB(skb).portid; NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; NETLINK_CB(new).creds = NETLINK_CB(skb).creds; skb_put_data(new, skb->data, len); return new; } static unsigned int netlink_tap_net_id; struct netlink_tap_net { struct list_head netlink_tap_all; struct mutex netlink_tap_lock; }; int netlink_add_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); if (unlikely(nt->dev->type != ARPHRD_NETLINK)) return -EINVAL; mutex_lock(&nn->netlink_tap_lock); list_add_rcu(&nt->list, &nn->netlink_tap_all); mutex_unlock(&nn->netlink_tap_lock); __module_get(nt->module); return 0; } EXPORT_SYMBOL_GPL(netlink_add_tap); static int __netlink_remove_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); bool found = false; struct netlink_tap *tmp; mutex_lock(&nn->netlink_tap_lock); list_for_each_entry(tmp, &nn->netlink_tap_all, list) { if (nt == tmp) { list_del_rcu(&nt->list); found = true; goto out; } } pr_warn("__netlink_remove_tap: %p not found\n", nt); out: mutex_unlock(&nn->netlink_tap_lock); if (found) module_put(nt->module); return found ? 0 : -ENODEV; } int netlink_remove_tap(struct netlink_tap *nt) { int ret; ret = __netlink_remove_tap(nt); synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(netlink_remove_tap); static __net_init int netlink_tap_init_net(struct net *net) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); INIT_LIST_HEAD(&nn->netlink_tap_all); mutex_init(&nn->netlink_tap_lock); return 0; } static struct pernet_operations netlink_tap_net_ops = { .init = netlink_tap_init_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), }; static bool netlink_filter_tap(const struct sk_buff *skb) { struct sock *sk = skb->sk; /* We take the more conservative approach and * whitelist socket protocols that may pass. */ switch (sk->sk_protocol) { case NETLINK_ROUTE: case NETLINK_USERSOCK: case NETLINK_SOCK_DIAG: case NETLINK_NFLOG: case NETLINK_XFRM: case NETLINK_FIB_LOOKUP: case NETLINK_NETFILTER: case NETLINK_GENERIC: return true; } return false; } static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; struct sock *sk = skb->sk; int ret = -ENOMEM; if (!net_eq(dev_net(dev), sock_net(sk))) return 0; dev_hold(dev); if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); } dev_put(dev); return ret; } static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn) { int ret; struct netlink_tap *tmp; if (!netlink_filter_tap(skb)) return; list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) { ret = __netlink_deliver_tap_skb(skb, tmp->dev); if (unlikely(ret)) break; } } static void netlink_deliver_tap(struct net *net, struct sk_buff *skb) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); rcu_read_lock(); if (unlikely(!list_empty(&nn->netlink_tap_all))) __netlink_deliver_tap(skb, nn); rcu_read_unlock(); } static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, struct sk_buff *skb) { if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) netlink_deliver_tap(sock_net(dst), skb); } static void netlink_overrun(struct sock *sk) { if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } atomic_inc(&sk->sk_drops); } static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); } static void netlink_skb_destructor(struct sk_buff *skb) { if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) vfree_atomic(skb->head); skb->head = NULL; } if (skb->sk != NULL) sock_rfree(skb); } static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static void netlink_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves * this, _but_ remember, it adds useless work on UP machines. */ void netlink_table_grab(void) __acquires(nl_table_lock) { might_sleep(); write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&nl_table_wait, &wait); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&nl_table_users) == 0) break; write_unlock_irq(&nl_table_lock); schedule(); write_lock_irq(&nl_table_lock); } __set_current_state(TASK_RUNNING); remove_wait_queue(&nl_table_wait, &wait); } } void netlink_table_ungrab(void) __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); wake_up(&nl_table_wait); } static inline void netlink_lock_table(void) { unsigned long flags; /* read_lock() synchronizes us to netlink_table_grab */ read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); read_unlock_irqrestore(&nl_table_lock, flags); } static inline void netlink_unlock_table(void) { if (atomic_dec_and_test(&nl_table_users)) wake_up(&nl_table_wait); } struct netlink_compare_arg { possible_net_t pnet; u32 portid; }; /* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ #define netlink_compare_arg_len \ (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) static inline int netlink_compare(struct rhashtable_compare_arg *arg, const void *ptr) { const struct netlink_compare_arg *x = arg->key; const struct netlink_sock *nlk = ptr; return nlk->portid != x->portid || !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); } static void netlink_compare_arg_init(struct netlink_compare_arg *arg, struct net *net, u32 portid) { memset(arg, 0, sizeof(*arg)); write_pnet(&arg->pnet, net); arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, net, portid); return rhashtable_lookup_fast(&table->hash, &arg, netlink_rhashtable_params); } static int __netlink_insert(struct netlink_table *table, struct sock *sk) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); return rhashtable_lookup_insert_key(&table->hash, &arg, &nlk_sk(sk)->node, netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { struct netlink_table *table = &nl_table[protocol]; struct sock *sk; rcu_read_lock(); sk = __netlink_lookup(table, portid, net); if (sk) sock_hold(sk); rcu_read_unlock(); return sk; } static const struct proto_ops netlink_ops; static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; unsigned long mask; unsigned int i; struct listeners *listeners; listeners = nl_deref_protected(tbl->listeners); if (!listeners) return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ } static int netlink_insert(struct sock *sk, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; int err; lock_sock(sk); err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; if (nlk_sk(sk)->bound) goto err; /* portid can be read locklessly from netlink_getname(). */ WRITE_ONCE(nlk_sk(sk)->portid, portid); sock_hold(sk); err = __netlink_insert(table, sk); if (err) { /* In case the hashtable backend returns with -EBUSY * from here, it must not escape to the caller. */ if (unlikely(err == -EBUSY)) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; sock_put(sk); goto err; } /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); /* Paired with lockless reads from netlink_bind(), * netlink_connect() and netlink_sendmsg(). */ WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); return err; } static void netlink_remove(struct sock *sk) { struct netlink_table *table; table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) { WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { __sk_del_bind_node(sk); netlink_update_listeners(sk); } if (sk->sk_protocol == NETLINK_GENERIC) atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } static struct proto netlink_proto = { .name = "NETLINK", .owner = THIS_MODULE, .obj_size = sizeof(struct netlink_sock), }; static int __netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct netlink_sock *nlk; sock->ops = &netlink_ops; sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); nlk = nlk_sk(sk); mutex_init(&nlk->nl_cb_mutex); lockdep_set_class_and_name(&nlk->nl_cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; return 0; } static int netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct module *module = NULL; struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release)(struct sock *sock, unsigned long *groups); int err = 0; sock->state = SS_UNCONNECTED; if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES if (!nl_table[protocol].registered) { netlink_unlock_table(); request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); netlink_lock_table(); } #endif if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; else err = -EPROTONOSUPPORT; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; release = nl_table[protocol].release; netlink_unlock_table(); if (err < 0) goto out; err = __netlink_create(net, sock, protocol, kern); if (err < 0) goto out_module; sock_prot_inuse_add(net, &netlink_proto, 1); nlk = nlk_sk(sock->sk); nlk->module = module; nlk->netlink_bind = bind; nlk->netlink_unbind = unbind; nlk->netlink_release = release; out: return err; out_module: module_put(module); goto out; } static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; kfree(nlk->groups); nlk->groups = NULL; if (!refcount_dec_and_test(&sk->sk_refcnt)) return; sk_free(sk); } static int netlink_release(struct socket *sock) { struct sock *sk = sock->sk; struct netlink_sock *nlk; if (!sk) return 0; netlink_remove(sk); sock_orphan(sk); nlk = nlk_sk(sk); /* * OK. Socket is unlinked, any packets that arrive now * will be purged. */ if (nlk->netlink_release) nlk->netlink_release(sk, nlk->groups); /* must not acquire netlink_table_lock in any way again before unbind * and notifying genetlink is done as otherwise it might deadlock */ if (nlk->netlink_unbind) { int i; for (i = 0; i < nlk->ngroups; i++) if (test_bit(i, nlk->groups)) nlk->netlink_unbind(sock_net(sk), i + 1); } if (sk->sk_protocol == NETLINK_GENERIC && atomic_dec_return(&genl_sk_destructing_cnt) == 0) wake_up(&genl_sk_destructing_waitq); sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); skb_queue_purge(&sk->sk_write_queue); if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, .portid = nlk->portid, }; blocking_notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); } /* Terminate any outstanding dump */ if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); } module_put(nlk->module); if (netlink_is_kernel(sk)) { netlink_table_grab(); BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { struct listeners *old; old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].unbind = NULL; nl_table[sk->sk_protocol].flags = 0; nl_table[sk->sk_protocol].registered = 0; } netlink_table_ungrab(); } sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); /* Because struct net might disappear soon, do not keep a pointer. */ if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); /* Because of deferred_put_nlk_sk and use of work queue, * it is possible netns will be freed before this socket. */ sock_net_set(sk, &init_net); __netns_tracker_alloc(&init_net, &sk->ns_tracker, false, GFP_KERNEL); } call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_table *table = &nl_table[sk->sk_protocol]; s32 portid = task_tgid_vnr(current); int err; s32 rover = -4096; bool ok; retry: cond_resched(); rcu_read_lock(); ok = !__netlink_lookup(table, portid, net); rcu_read_unlock(); if (!ok) { /* Bind collision, search negative portid values. */ if (rover == -4096) /* rover will be in range [S32_MIN, -4097] */ rover = S32_MIN + get_random_u32_below(-4096 - S32_MIN); else if (rover >= -4096) rover = -4097; portid = rover--; goto retry; } err = netlink_insert(sk, portid); if (err == -EADDRINUSE) goto retry; /* If 2 threads race to autobind, that is fine. */ if (err == -EBUSY) err = 0; return err; } /** * __netlink_ns_capable - General netlink message capability test * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { return ((nsp->flags & NETLINK_SKB_DST) || file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable); /** * netlink_ns_capable - General netlink message capability test * @skb: socket buffer holding a netlink command from userspace * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) { return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); } EXPORT_SYMBOL(netlink_ns_capable); /** * netlink_capable - Netlink global message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, &init_user_ns, cap); } EXPORT_SYMBOL(netlink_capable); /** * netlink_net_capable - Netlink network namespace message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); } EXPORT_SYMBOL(netlink_net_capable); static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); } static void netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) { struct netlink_sock *nlk = nlk_sk(sk); if (nlk->subscriptions && !subscriptions) __sk_del_bind_node(sk); else if (!nlk->subscriptions && subscriptions) sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); nlk->subscriptions = subscriptions; } static int netlink_realloc_groups(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int groups; unsigned long *new_groups; int err = 0; netlink_table_grab(); groups = nl_table[sk->sk_protocol].groups; if (!nl_table[sk->sk_protocol].registered) { err = -ENOENT; goto out_unlock; } if (nlk->ngroups >= groups) goto out_unlock; new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); if (new_groups == NULL) { err = -ENOMEM; goto out_unlock; } memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); nlk->groups = new_groups; nlk->ngroups = groups; out_unlock: netlink_table_ungrab(); return err; } static void netlink_undo_bind(int group, long unsigned int groups, struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); int undo; if (!nlk->netlink_unbind) return; for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) nlk->netlink_unbind(sock_net(sk), undo + 1); } static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; if (nladdr->nl_family != AF_NETLINK) return -EINVAL; groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; } if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; /* Paired with WRITE_ONCE() in netlink_insert() */ bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); if (nladdr->nl_pid != nlk->portid) return -EINVAL; } if (nlk->netlink_bind && groups) { int group; /* nl_groups is a u32, so cap the maximum groups we can bind */ for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); if (!err) continue; netlink_undo_bind(group, groups, sk); return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) goto unlock; netlink_unlock_table(); netlink_table_grab(); netlink_update_subscriptions(sk, nlk->subscriptions + hweight32(groups) - hweight32(nlk->groups[0])); nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; netlink_update_listeners(sk); netlink_table_ungrab(); return 0; unlock: netlink_unlock_table(); return err; } static int netlink_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { int err = 0; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; if (alen < sizeof(addr->sa_family)) return -EINVAL; if (addr->sa_family == AF_UNSPEC) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, 0); WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) return -EINVAL; if (alen < sizeof(struct sockaddr_nl)) return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; /* No need for barriers here as we return to user-space without * using any of the bound attributes. * Paired with WRITE_ONCE() in netlink_insert(). */ if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; } static int netlink_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; if (peer) { /* Paired with WRITE_ONCE() in netlink_connect() */ nladdr->nl_pid = READ_ONCE(nlk->dst_portid); nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* try to hand this ioctl down to the NIC drivers. */ return -ENOIOCTLCMD; } static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; struct netlink_sock *nlk; sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); if (!sock) return ERR_PTR(-ECONNREFUSED); /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); /* dst_portid and sk_state can be changed in netlink_connect() */ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } return sock; } struct sock *netlink_getsockbyfd(int fd) { CLASS(fd, f)(fd); struct inode *inode; struct sock *sock; if (fd_empty(f)) return ERR_PTR(-EBADF); inode = file_inode(fd_file(f)); if (!S_ISSOCK(inode->i_mode)) return ERR_PTR(-ENOTSOCK); sock = SOCKET_I(inode)->sk; if (sock->sk_family != AF_NETLINK) return ERR_PTR(-EINVAL); sock_hold(sock); return sock; } struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { size_t head_size = SKB_HEAD_ALIGN(size); struct sk_buff *skb; void *data; if (head_size <= PAGE_SIZE || broadcast) return alloc_skb(size, GFP_KERNEL); data = kvmalloc(head_size, GFP_KERNEL); if (!data) return NULL; skb = __build_skb(data, head_size); if (!skb) kvfree(data); else if (is_vmalloc_addr(data)) skb->destructor = netlink_skb_destructor; return skb; } /* * Attach a skb to a netlink socket. * The caller must hold a reference to the destination socket. On error, the * reference is dropped. The skb is not send to the destination, just all * all error checks are performed and memory in the queue is reserved. * Return values: * < 0: error. skb freed, reference to sock dropped. * 0: continue * 1: repeat lookup - reference dropped while waiting for socket memory. */ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { struct netlink_sock *nlk; nlk = nlk_sk(sk); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(NETLINK_S_CONGESTED, &nlk->state))) { DECLARE_WAITQUEUE(wait, current); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); kfree_skb(skb); return -EAGAIN; } __set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&nlk->wait, &wait); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); sock_put(sk); if (signal_pending(current)) { kfree_skb(skb); return sock_intr_errno(*timeo); } return 1; } netlink_skb_set_owner_r(skb, sk); return 0; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; netlink_deliver_tap(sock_net(sk), skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } int netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = __netlink_sendskb(sk, skb); sock_put(sk); return len; } void netlink_detachskb(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); sock_put(sk); } static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) { int delta; skb_assert_len(skb); WARN_ON(skb->sk != NULL); delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, allocation); if (!nskb) return skb; consume_skb(skb); skb = nskb; } pskb_expand_head(skb, 0, -delta, (allocation & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); return skb; } static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, struct sock *ssk) { int ret; struct netlink_sock *nlk = nlk_sk(sk); ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); nlk->netlink_rcv(skb); consume_skb(skb); } else { kfree_skb(skb); } sock_put(sk); return ret; } int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 portid, int nonblock) { struct sock *sk; int err; long timeo; skb = netlink_trim(skb, gfp_any()); timeo = sock_sndtimeo(ssk, nonblock); retry: sk = netlink_getsockbyportid(ssk, portid); if (IS_ERR(sk)) { kfree_skb(skb); return PTR_ERR(sk); } if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb, ssk); if (sk_filter(sk, skb)) { err = skb->len; kfree_skb(skb); sock_put(sk); return err; } err = netlink_attachskb(sk, skb, &timeo, ssk); if (err == 1) goto retry; if (err) return err; return netlink_sendskb(sk, skb); } EXPORT_SYMBOL(netlink_unicast); int netlink_has_listeners(struct sock *sk, unsigned int group) { int res = 0; struct listeners *listeners; BUG_ON(!netlink_is_kernel(sk)); rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); } EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); } return -1; } struct netlink_broadcast_data { struct sock *exclude_sk; struct net *net; u32 portid; u32 group; int failure; int delivery_failure; int congested; int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); void *tx_data; }; static void do_one_broadcast(struct sock *sk, struct netlink_broadcast_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int val; if (p->exclude_sk == sk) return; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) return; if (!net_eq(sock_net(sk), p->net)) { if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) return; if (!peernet_has_id(sock_net(sk), p->net)) return; if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, CAP_NET_BROADCAST)) return; } if (p->failure) { netlink_overrun(sk); return; } sock_hold(sk); if (p->skb2 == NULL) { if (skb_shared(p->skb)) { p->skb2 = skb_clone(p->skb, p->allocation); } else { p->skb2 = skb_get(p->skb); /* * skb ownership may have been set when * delivered to a previous socket. */ skb_orphan(p->skb2); } } if (p->skb2 == NULL) { netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; goto out; } if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) NETLINK_CB(p->skb2).nsid_is_set = true; val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; p->skb2 = NULL; } out: sock_put(sk); } int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation, netlink_filter_fn filter, void *filter_data) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct sock *sk; skb = netlink_trim(skb, allocation); info.exclude_sk = ssk; info.net = net; info.portid = portid; info.group = group; info.failure = 0; info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; info.skb = skb; info.skb2 = NULL; info.tx_filter = filter; info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ netlink_lock_table(); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); netlink_unlock_table(); if (info.delivery_failure) { kfree_skb(info.skb2); return -ENOBUFS; } consume_skb(info.skb2); if (info.delivered) { if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } return -ESRCH; } EXPORT_SYMBOL(netlink_broadcast_filtered); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation) { return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, NULL, NULL); } EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; u32 portid; u32 group; int code; }; static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int ret = 0; if (sk == p->exclude_sk) goto out; if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { ret = 1; goto out; } WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; } /** * netlink_set_err - report error to broadcast listeners * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_NO_ENOBUFS socket option. */ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; unsigned long flags; struct sock *sk; int ret = 0; info.exclude_sk = ssk; info.portid = portid; info.group = group; /* sk->sk_err wants a positive error value */ info.code = -code; read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); /* must be called with netlink table grabbed */ static void netlink_update_socket_mc(struct netlink_sock *nlk, unsigned int group, int is_new) { int old, new = !!is_new, subscriptions; old = test_bit(group - 1, nlk->groups); subscriptions = nlk->subscriptions - old + new; __assign_bit(group - 1, nlk->groups, new); netlink_update_subscriptions(&nlk->sk, subscriptions); netlink_update_listeners(&nlk->sk); } static int netlink_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; int nr = -1; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (optlen >= sizeof(int) && copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case NETLINK_PKTINFO: nr = NETLINK_F_RECV_PKTINFO; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { int err; if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; if (!val || val - 1 >= nlk->ngroups) return -EINVAL; if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { err = nlk->netlink_bind(sock_net(sk), val); if (err) return err; } netlink_table_grab(); netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); break; } case NETLINK_BROADCAST_ERROR: nr = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); if (val) { clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); } break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; nr = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: nr = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: nr = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: nr = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (nr >= 0) assign_bit(nr, &nlk->flags, val); return 0; } static int netlink_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int flag; int len, val; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case NETLINK_PKTINFO: flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { int pos, idx, shift, err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; idx = pos / sizeof(unsigned long); shift = (pos % sizeof(unsigned long)) * 8; if (put_user((u32)(nlk->groups[idx] >> shift), (u32 __user *)(optval + pos))) { err = -EFAULT; break; } } if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; } case NETLINK_LISTEN_ALL_NSID: flag = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: flag = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: flag = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = test_bit(flag, &nlk->flags); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct nl_pktinfo info; info.group = NETLINK_CB(skb).dst_group; put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { if (!NETLINK_CB(skb).nsid_is_set) return; put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), &NETLINK_CB(skb).nsid); } static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); u32 dst_portid; u32 dst_group; struct sk_buff *skb; int err; struct scm_cookie scm; u32 netlink_skb_flags = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (len == 0) { pr_warn_once("Zero length message leads to an empty skb\n"); return -ENODATA; } err = scm_send(sock, msg, &scm, true); if (err < 0) return err; if (msg->msg_namelen) { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_nl)) goto out; if (addr->nl_family != AF_NETLINK) goto out; dst_portid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { /* Paired with WRITE_ONCE() in netlink_connect() */ dst_portid = READ_ONCE(nlk->dst_portid); dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; } else { /* Ensure nlk is hashed and visible. */ smp_rmb(); } err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = netlink_alloc_large_skb(len, dst_group); if (skb == NULL) goto out; NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = scm.creds; NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_from_msg(skb_put(skb, len), msg, len)) { kfree_skb(skb); goto out; } err = security_netlink_send(sk, skb); if (err) { kfree_skb(skb); goto out; } if (dst_group) { refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); out: scm_destroy(&scm); return err; } static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; if (flags & MSG_OOB) return -EOPNOTSUPP; copied = 0; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; data_skb = skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES if (unlikely(skb_shinfo(skb)->frag_list)) { /* * If this skb has a frag_list, then here that means that we * will have to use the frag_list skb's data for compat tasks * and the regular skb's data for normal (non-compat) tasks. * * If we need to send the compat skb, assign it to the * 'data_skb' variable so that it will be used below for data * copying. We keep 'skb' for everything else, including * freeing both later. */ if (flags & MSG_CMSG_COMPAT) data_skb = skb_shinfo(skb)->frag_list; } #endif /* Record the max length of recvmsg() calls for future allocations */ max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); max_recvmsg_len = min_t(size_t, max_recvmsg_len, SKB_WITH_OVERHEAD(32768)); WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); addr->nl_family = AF_NETLINK; addr->nl_pad = 0; addr->nl_pid = NETLINK_CB(skb).portid; addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); msg->msg_namelen = sizeof(*addr); } if (nlk_test_bit(RECV_PKTINFO, sk)) netlink_cmsg_recv_pktinfo(msg, skb); if (nlk_test_bit(LISTEN_ALL_NSID, sk)) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); scm.creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = data_skb->len; skb_free_datagram(sk, skb); if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk, false); if (ret) { WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } scm_recv(sock, msg, &scm, flags); out: netlink_rcv_wake(sk); return err ? : copied; } static void netlink_data_ready(struct sock *sk) { BUG(); } /* * We export these functions to other modules. They provide a * complete set of kernel non-blocking support for message * queueing. */ struct sock * __netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; unsigned int groups; BUG_ON(!nl_table); if (unit < 0 || unit >= MAX_LINKS) return NULL; if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; if (__netlink_create(net, sock, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; if (!cfg || cfg->groups < 32) groups = 32; else groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; if (cfg && cfg->input) nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, 0)) goto out_sock_release; nlk = nlk_sk(sk); set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); netlink_table_grab(); if (!nl_table[unit].registered) { nl_table[unit].groups = groups; rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; nl_table[unit].unbind = cfg->unbind; nl_table[unit].release = cfg->release; nl_table[unit].flags = cfg->flags; } nl_table[unit].registered = 1; } else { kfree(listeners); nl_table[unit].registered++; } netlink_table_ungrab(); return sk; out_sock_release: kfree(listeners); netlink_kernel_release(sk); return NULL; out_sock_release_nosk: sock_release(sock); return NULL; } EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) { if (sk == NULL || sk->sk_socket == NULL) return; sock_release(sk->sk_socket); } EXPORT_SYMBOL(netlink_kernel_release); int __netlink_change_ngroups(struct sock *sk, unsigned int groups) { struct listeners *new, *old; struct netlink_table *tbl = &nl_table[sk->sk_protocol]; if (groups < 32) groups = 32; if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); kfree_rcu(old, rcu); } tbl->groups = groups; return 0; } /** * netlink_change_ngroups - change number of multicast groups * * This changes the number of multicast groups that are available * on a certain netlink family. Note that it is not possible to * change the number of groups to below 32. Also note that it does * not implicitly call netlink_clear_multicast_users() when the * number of groups is reduced. * * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). * @groups: The new number of groups. */ int netlink_change_ngroups(struct sock *sk, unsigned int groups) { int err; netlink_table_grab(); err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); return err; } void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; struct hlist_node *tmp; sk_for_each_bound_safe(sk, tmp, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); nlh = skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; nlh->nlmsg_pid = portid; nlh->nlmsg_seq = seq; if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); return nlh; } EXPORT_SYMBOL(__nlmsg_put); static size_t netlink_ack_tlv_len(struct netlink_sock *nlk, int err, const struct netlink_ext_ack *extack) { size_t tlvlen; if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) return 0; tlvlen = 0; if (extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); if (extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); /* Following attributes are only reported as error (not warning) */ if (!err) return tlvlen; if (extack->bad_attr) tlvlen += nla_total_size(sizeof(u32)); if (extack->policy) tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); if (extack->miss_type) tlvlen += nla_total_size(sizeof(u32)); if (extack->miss_nest) tlvlen += nla_total_size(sizeof(u32)); return tlvlen; } static bool nlmsg_check_in_payload(const struct nlmsghdr *nlh, const void *addr) { return !WARN_ON(addr < nlmsg_data(nlh) || addr - (const void *) nlh >= nlh->nlmsg_len); } static void netlink_ack_tlv_fill(struct sk_buff *skb, const struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { if (extack->_msg) WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, extack->cookie_len, extack->cookie)); if (!err) return; if (extack->bad_attr && nlmsg_check_in_payload(nlh, extack->bad_attr)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - (const u8 *)nlh)); if (extack->policy) netlink_policy_dump_write_attr(skb, extack->policy, NLMSGERR_ATTR_POLICY); if (extack->miss_type) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, extack->miss_type)); if (extack->miss_nest && nlmsg_check_in_payload(nlh, extack->miss_nest)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, (u8 *)extack->miss_nest - (const u8 *)nlh)); } /* * It looks a bit ugly. * It would be better to create kernel thread. */ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, struct netlink_callback *cb, struct netlink_ext_ack *extack) { struct nlmsghdr *nlh; size_t extack_len; nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), NLM_F_MULTI | cb->answer_flags); if (WARN_ON(!nlh)) return -ENOBUFS; nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); extack_len = netlink_ack_tlv_len(nlk, nlk->dump_done_errno, extack); if (extack_len) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (skb_tailroom(skb) >= extack_len) { netlink_ack_tlv_fill(skb, cb->nlh, nlk->dump_done_errno, extack); nlmsg_end(skb, nlh); } } return 0; } static int netlink_dump(struct sock *sk, bool lock_taken) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; int alloc_size; if (!lock_taken) mutex_lock(&nlk->nl_cb_mutex); if (!nlk->cb_running) { err = -EINVAL; goto errout_skb; } if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 32KiB allocation * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); if (alloc_min_size < max_recvmsg_len) { alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; skb = alloc_skb(alloc_size, GFP_KERNEL); } if (!skb) goto errout_skb; /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as * could fit within the allocated skb. skb is typically allocated * with larger space than required (could be as much as near 2x the * requested size with align to next power of 2 approach). Allowing * dump to use the excess space makes it difficult for a user to have a * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); /* Make sure malicious BPF programs can not read unitialized memory * from skb->head -> skb->data */ skb_reset_network_header(skb); skb_reset_mac_header(skb); netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { cb->extack = &extack; nlk->dump_done_errno = cb->dump(skb, cb); /* EMSGSIZE plus something already in the skb means * that there's more to dump but current skb has filled up. * If the callback really wants to return EMSGSIZE to user space * it needs to do so again, on the next cb->dump() call, * without putting data in the skb. */ if (nlk->dump_done_errno == -EMSGSIZE && skb->len) nlk->dump_done_errno = skb->len; cb->extack = NULL; } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(&nlk->nl_cb_mutex); if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); return 0; } if (netlink_dump_done(nlk, skb, cb, &extack)) goto errout_skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES /* frag_list skb's data is used for compat tasks * and the regular skb's data for normal (non-compat) tasks. * See netlink_recvmsg(). */ if (unlikely(skb_shinfo(skb)->frag_list)) { if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) goto errout_skb; } #endif if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(&nlk->nl_cb_mutex); module_put(module); consume_skb(skb); return 0; errout_skb: mutex_unlock(&nlk->nl_cb_mutex); kfree_skb(skb); return err; } int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { struct netlink_callback *cb; struct netlink_sock *nlk; struct sock *sk; int ret; refcount_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { ret = -ECONNREFUSED; goto error_free; } nlk = nlk_sk(sk); mutex_lock(&nlk->nl_cb_mutex); /* A dump is in progress... */ if (nlk->cb_running) { ret = -EBUSY; goto error_unlock; } /* add reference of module which cb->dump belongs to */ if (!try_module_get(control->module)) { ret = -EPROTONOSUPPORT; goto error_unlock; } cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; cb->flags = control->flags; cb->skb = skb; cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); if (control->start) { cb->extack = control->extack; ret = control->start(cb); cb->extack = NULL; if (ret) goto error_put; } WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; ret = netlink_dump(sk, true); sock_put(sk); if (ret) return ret; /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ return -EINTR; error_put: module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(&nlk->nl_cb_mutex); error_free: kfree_skb(skb); return ret; } EXPORT_SYMBOL(__netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct sk_buff *skb; struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); unsigned int flags = 0; size_t tlvlen; /* Error messages get the original request appened, unless the user * requests to cap the error message, and get extra error data if * requested. */ if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; tlvlen = netlink_ack_tlv_len(nlk, err, extack); if (tlvlen) flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(*errmsg), flags); if (!rep) goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; errmsg->msg = *nlh; if (!(flags & NLM_F_CAPPED)) { if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } if (tlvlen) netlink_ack_tlv_fill(skb, nlh, err, extack); nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); return; err_bad_put: nlmsg_free(skb); err_skb: WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; while (skb->len >= nlmsg_total_size(0)) { int msglen; memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return 0; /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) goto ack; /* Skip control messages */ if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) netlink_ack(skb, nlh, err, &extack); skip: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } return 0; } EXPORT_SYMBOL(netlink_rcv_skb); /** * nlmsg_notify - send a notification netlink message * @sk: netlink socket to use * @skb: notification message * @portid: destination netlink portid for reports or 0 * @group: destination multicast group or 0 * @report: 1 to report back, 0 to disable * @flags: allocation flags */ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags) { int err = 0; if (group) { int exclude_portid = 0; if (report) { refcount_inc(&skb->users); exclude_portid = portid; } /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); if (err == -ESRCH) err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); if (!err) err = err2; } return err; } EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { struct seq_net_private p; struct rhashtable_iter hti; int link; }; static void netlink_walk_start(struct nl_seq_iter *iter) { rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti); rhashtable_walk_start(&iter->hti); } static void netlink_walk_stop(struct nl_seq_iter *iter) { rhashtable_walk_stop(&iter->hti); rhashtable_walk_exit(&iter->hti); } static void *__netlink_seq_next(struct seq_file *seq) { struct nl_seq_iter *iter = seq->private; struct netlink_sock *nlk; do { for (;;) { nlk = rhashtable_walk_next(&iter->hti); if (IS_ERR(nlk)) { if (PTR_ERR(nlk) == -EAGAIN) continue; return nlk; } if (nlk) break; netlink_walk_stop(iter); if (++iter->link >= MAX_LINKS) return NULL; netlink_walk_start(iter); } } while (sock_net(&nlk->sk) != seq_file_net(seq)); return nlk; } static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) __acquires(RCU) { struct nl_seq_iter *iter = seq->private; void *obj = SEQ_START_TOKEN; loff_t pos; iter->link = 0; netlink_walk_start(iter); for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) obj = __netlink_seq_next(seq); return obj; } static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return __netlink_seq_next(seq); } static void netlink_native_seq_stop(struct seq_file *seq, void *v) { struct nl_seq_iter *iter = seq->private; if (iter->link >= MAX_LINKS) return; netlink_walk_stop(iter); } static int netlink_native_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk Eth Pid Groups " "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8lu\n", s, s->sk_protocol, nlk->portid, nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) ); } return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__netlink { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct netlink_sock *, sk); }; DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk) static int netlink_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__netlink ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk = nlk_sk((struct sock *)v); return bpf_iter_run_prog(prog, &ctx); } static int netlink_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return netlink_native_seq_show(seq, v); if (v != SEQ_START_TOKEN) return netlink_prog_seq_show(prog, &meta, v); return 0; } static void netlink_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)netlink_prog_seq_show(prog, &meta, v); } netlink_native_seq_stop(seq, v); } #else static int netlink_seq_show(struct seq_file *seq, void *v) { return netlink_native_seq_show(seq, v); } static void netlink_seq_stop(struct seq_file *seq, void *v) { netlink_native_seq_stop(seq, v); } #endif static const struct seq_operations netlink_seq_ops = { .start = netlink_seq_start, .next = netlink_seq_next, .stop = netlink_seq_stop, .show = netlink_seq_show, }; #endif int netlink_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_register_notifier); int netlink_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_unregister_notifier); static const struct proto_ops netlink_ops = { .family = PF_NETLINK, .owner = THIS_MODULE, .release = netlink_release, .bind = netlink_bind, .connect = netlink_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, .poll = datagram_poll, .ioctl = netlink_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = netlink_setsockopt, .getsockopt = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, .mmap = sock_no_mmap, }; static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ }; static int __net_init netlink_net_init(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops, sizeof(struct nl_seq_iter))) return -ENOMEM; #endif return 0; } static void __net_exit netlink_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("netlink", net->proc_net); #endif } static void __init netlink_add_usersock_entry(void) { struct listeners *listeners; int groups = 32; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); netlink_table_grab(); nl_table[NETLINK_USERSOCK].groups = groups; rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); nl_table[NETLINK_USERSOCK].module = THIS_MODULE; nl_table[NETLINK_USERSOCK].registered = 1; nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; netlink_table_ungrab(); } static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) { const struct netlink_sock *nlk = data; struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); } static const struct rhashtable_params netlink_rhashtable_params = { .head_offset = offsetof(struct netlink_sock, node), .key_len = netlink_compare_arg_len, .obj_hashfn = netlink_hash, .obj_cmpfn = netlink_compare, .automatic_shrinking = true, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) BTF_ID_LIST(btf_netlink_sock_id) BTF_ID(struct, netlink_sock) static const struct bpf_iter_seq_info netlink_seq_info = { .seq_ops = &netlink_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct nl_seq_iter), }; static struct bpf_iter_reg netlink_reg_info = { .target = "netlink", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__netlink, sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &netlink_seq_info, }; static int __init bpf_iter_register(void) { netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id; return bpf_iter_reg_target(&netlink_reg_info); } #endif static int __init netlink_proto_init(void) { int i; int err = proto_register(&netlink_proto, 0); if (err != 0) goto out; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) err = bpf_iter_register(); if (err) goto out; #endif BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) goto panic; for (i = 0; i < MAX_LINKS; i++) { if (rhashtable_init(&nl_table[i].hash, &netlink_rhashtable_params) < 0) goto panic; } netlink_add_usersock_entry(); sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); register_pernet_subsys(&netlink_tap_net_ops); /* The netlink device handler may be needed early. */ rtnetlink_init(); out: return err; panic: panic("netlink_init: Cannot allocate nl_table\n"); } core_initcall(netlink_proto_init); |
| 8 8 8 8 2 8 8 8 8 10 9 8 8 8 8 11 2 1 1 2 1 1 1 1 1 2 2 2 2 2 2 2 9 9 9 8 9 9 9 8 8 8 8 8 8 8 8 8 2 8 1 1 1 8 8 8 9 9 8 8 8 8 9 8 8 9 8 9 10 11 11 12 1 11 10 10 10 10 10 11 11 11 11 11 11 11 12 13 12 1 11 1 1 11 11 2 2 2 2 1 1 9 1 1 1 2 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 5 1 1 2 1 1 1 1 1 1 1 19 1 1 6 3 2 5 7 5 1 1 1 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * GICv3 ITS emulation * * Copyright (C) 2015,2016 ARM Ltd. * Author: Andre Przywara <andre.przywara@arm.com> */ #include <linux/cpu.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/list_sort.h> #include <linux/irqchip/arm-gic-v3.h> #include <asm/kvm_emulate.h> #include <asm/kvm_arm.h> #include <asm/kvm_mmu.h> #include "vgic.h" #include "vgic-mmio.h" static struct kvm_device_ops kvm_arm_vgic_its_ops; static int vgic_its_save_tables_v0(struct vgic_its *its); static int vgic_its_restore_tables_v0(struct vgic_its *its); static int vgic_its_commit_v0(struct vgic_its *its); static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, struct kvm_vcpu *filter_vcpu, bool needs_inv); #define vgic_its_read_entry_lock(i, g, valp, t) \ ({ \ int __sz = vgic_its_get_abi(i)->t##_esz; \ struct kvm *__k = (i)->dev->kvm; \ int __ret; \ \ BUILD_BUG_ON(NR_ITS_ABIS == 1 && \ sizeof(*(valp)) != ABI_0_ESZ); \ if (NR_ITS_ABIS > 1 && \ KVM_BUG_ON(__sz != sizeof(*(valp)), __k)) \ __ret = -EINVAL; \ else \ __ret = kvm_read_guest_lock(__k, (g), \ valp, __sz); \ __ret; \ }) #define vgic_its_write_entry_lock(i, g, val, t) \ ({ \ int __sz = vgic_its_get_abi(i)->t##_esz; \ struct kvm *__k = (i)->dev->kvm; \ typeof(val) __v = (val); \ int __ret; \ \ BUILD_BUG_ON(NR_ITS_ABIS == 1 && \ sizeof(__v) != ABI_0_ESZ); \ if (NR_ITS_ABIS > 1 && \ KVM_BUG_ON(__sz != sizeof(__v), __k)) \ __ret = -EINVAL; \ else \ __ret = vgic_write_guest_lock(__k, (g), \ &__v, __sz); \ __ret; \ }) /* * Creates a new (reference to a) struct vgic_irq for a given LPI. * If this LPI is already mapped on another ITS, we increase its refcount * and return a pointer to the existing structure. * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq. * This function returns a pointer to the _unlocked_ structure. */ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, struct kvm_vcpu *vcpu) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, intid), *oldirq; unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ if (irq) return irq; irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!irq) return ERR_PTR(-ENOMEM); ret = xa_reserve_irq(&dist->lpi_xa, intid, GFP_KERNEL_ACCOUNT); if (ret) { kfree(irq); return ERR_PTR(ret); } INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; kref_init(&irq->refcount); irq->intid = intid; irq->target_vcpu = vcpu; irq->group = 1; xa_lock_irqsave(&dist->lpi_xa, flags); /* * There could be a race with another vgic_add_lpi(), so we need to * check that we don't add a second list entry with the same LPI. */ oldirq = xa_load(&dist->lpi_xa, intid); if (vgic_try_get_irq_kref(oldirq)) { /* Someone was faster with adding this LPI, lets use that. */ kfree(irq); irq = oldirq; goto out_unlock; } ret = xa_err(__xa_store(&dist->lpi_xa, intid, irq, 0)); if (ret) { xa_release(&dist->lpi_xa, intid); kfree(irq); } out_unlock: xa_unlock_irqrestore(&dist->lpi_xa, flags); if (ret) return ERR_PTR(ret); /* * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. * * Should any of these fail, behave as if we couldn't create the LPI * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); if (ret) { vgic_put_irq(kvm, irq); return ERR_PTR(ret); } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); if (ret) { vgic_put_irq(kvm, irq); return ERR_PTR(ret); } return irq; } struct its_device { struct list_head dev_list; /* the head for the list of ITTEs */ struct list_head itt_head; u32 num_eventid_bits; gpa_t itt_addr; u32 device_id; }; #define COLLECTION_NOT_MAPPED ((u32)~0) struct its_collection { struct list_head coll_list; u32 collection_id; u32 target_addr; }; #define its_is_collection_mapped(coll) ((coll) && \ ((coll)->target_addr != COLLECTION_NOT_MAPPED)) struct its_ite { struct list_head ite_list; struct vgic_irq *irq; struct its_collection *collection; u32 event_id; }; /** * struct vgic_its_abi - ITS abi ops and settings * @cte_esz: collection table entry size * @dte_esz: device table entry size * @ite_esz: interrupt translation table entry size * @save_tables: save the ITS tables into guest RAM * @restore_tables: restore the ITS internal structs from tables * stored in guest RAM * @commit: initialize the registers which expose the ABI settings, * especially the entry sizes */ struct vgic_its_abi { int cte_esz; int dte_esz; int ite_esz; int (*save_tables)(struct vgic_its *its); int (*restore_tables)(struct vgic_its *its); int (*commit)(struct vgic_its *its); }; #define ABI_0_ESZ 8 #define ESZ_MAX ABI_0_ESZ static const struct vgic_its_abi its_table_abi_versions[] = { [0] = { .cte_esz = ABI_0_ESZ, .dte_esz = ABI_0_ESZ, .ite_esz = ABI_0_ESZ, .save_tables = vgic_its_save_tables_v0, .restore_tables = vgic_its_restore_tables_v0, .commit = vgic_its_commit_v0, }, }; #define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions) inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its) { return &its_table_abi_versions[its->abi_rev]; } static int vgic_its_set_abi(struct vgic_its *its, u32 rev) { const struct vgic_its_abi *abi; its->abi_rev = rev; abi = vgic_its_get_abi(its); return abi->commit(its); } /* * Find and returns a device in the device table for an ITS. * Must be called with the its_lock mutex held. */ static struct its_device *find_its_device(struct vgic_its *its, u32 device_id) { struct its_device *device; list_for_each_entry(device, &its->device_list, dev_list) if (device_id == device->device_id) return device; return NULL; } /* * Find and returns an interrupt translation table entry (ITTE) for a given * Device ID/Event ID pair on an ITS. * Must be called with the its_lock mutex held. */ static struct its_ite *find_ite(struct vgic_its *its, u32 device_id, u32 event_id) { struct its_device *device; struct its_ite *ite; device = find_its_device(its, device_id); if (device == NULL) return NULL; list_for_each_entry(ite, &device->itt_head, ite_list) if (ite->event_id == event_id) return ite; return NULL; } /* To be used as an iterator this macro misses the enclosing parentheses */ #define for_each_lpi_its(dev, ite, its) \ list_for_each_entry(dev, &(its)->device_list, dev_list) \ list_for_each_entry(ite, &(dev)->itt_head, ite_list) #define GIC_LPI_OFFSET 8192 #define VITS_TYPER_IDBITS 16 #define VITS_MAX_EVENTID (BIT(VITS_TYPER_IDBITS) - 1) #define VITS_TYPER_DEVBITS 16 #define VITS_MAX_DEVID (BIT(VITS_TYPER_DEVBITS) - 1) #define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1) #define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1) /* * Finds and returns a collection in the ITS collection table. * Must be called with the its_lock mutex held. */ static struct its_collection *find_collection(struct vgic_its *its, int coll_id) { struct its_collection *collection; list_for_each_entry(collection, &its->collection_list, coll_list) { if (coll_id == collection->collection_id) return collection; } return NULL; } #define LPI_PROP_ENABLE_BIT(p) ((p) & LPI_PROP_ENABLED) #define LPI_PROP_PRIORITY(p) ((p) & 0xfc) /* * Reads the configuration data for a given LPI from guest memory and * updates the fields in struct vgic_irq. * If filter_vcpu is not NULL, applies only if the IRQ is targeting this * VCPU. Unconditionally applies if filter_vcpu is NULL. */ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, struct kvm_vcpu *filter_vcpu, bool needs_inv) { u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser); u8 prop; int ret; unsigned long flags; ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, &prop, 1); if (ret) return ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { irq->priority = LPI_PROP_PRIORITY(prop); irq->enabled = LPI_PROP_ENABLE_BIT(prop); if (!irq->hw) { vgic_queue_irq_unlock(kvm, irq, flags); return 0; } } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); return 0; } static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int ret = 0; unsigned long flags; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; ret = its_get_vlpi(irq->host_irq, &map); if (ret) return ret; if (map.vpe) atomic_dec(&map.vpe->vlpi_count); map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; atomic_inc(&map.vpe->vlpi_count); ret = its_map_vlpi(irq->host_irq, &map); } return ret; } static struct kvm_vcpu *collection_to_vcpu(struct kvm *kvm, struct its_collection *col) { return kvm_get_vcpu_by_id(kvm, col->target_addr); } /* * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI * is targeting) to the VGIC's view, which deals with target VCPUs. * Needs to be called whenever either the collection for a LPIs has * changed or the collection itself got retargeted. */ static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite) { struct kvm_vcpu *vcpu; if (!its_is_collection_mapped(ite->collection)) return; vcpu = collection_to_vcpu(kvm, ite->collection); update_affinity(ite->irq, vcpu); } /* * Updates the target VCPU for every LPI targeting this collection. * Must be called with the its_lock mutex held. */ static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its, struct its_collection *coll) { struct its_device *device; struct its_ite *ite; for_each_lpi_its(device, ite, its) { if (ite->collection != coll) continue; update_affinity_ite(kvm, ite); } } static u32 max_lpis_propbaser(u64 propbaser) { int nr_idbits = (propbaser & 0x1f) + 1; return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS); } /* * Sync the pending table pending bit of LPIs targeting @vcpu * with our own data structures. This relies on the LPI being * mapped before. */ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) { gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); struct vgic_dist *dist = &vcpu->kvm->arch.vgic; unsigned long intid, flags; struct vgic_irq *irq; int last_byte_offset = -1; int ret = 0; u8 pendmask; xa_for_each(&dist->lpi_xa, intid, irq) { int byte_offset, bit_nr; byte_offset = intid / BITS_PER_BYTE; bit_nr = intid % BITS_PER_BYTE; /* * For contiguously allocated LPIs chances are we just read * this very same byte in the last iteration. Reuse that. */ if (byte_offset != last_byte_offset) { ret = kvm_read_guest_lock(vcpu->kvm, pendbase + byte_offset, &pendmask, 1); if (ret) return ret; last_byte_offset = byte_offset; } irq = vgic_get_irq(vcpu->kvm, intid); if (!irq) continue; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu == vcpu) irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } return ret; } static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 reg = GITS_TYPER_PLPIS; /* * We use linear CPU numbers for redistributor addressing, * so GITS_TYPER.PTA is 0. * Also we force all PROPBASER registers to be the same, so * CommonLPIAff is 0 as well. * To avoid memory waste in the guest, we keep the number of IDBits and * DevBits low - as least for the time being. */ reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT; reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT; reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT; return extract_bytes(reg, addr & 7, len); } static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { u32 val; val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK; val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM; return val; } static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u32 rev = GITS_IIDR_REV(val); if (rev >= NR_ITS_ABIS) return -EINVAL; return vgic_its_set_abi(its, rev); } static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { switch (addr & 0xffff) { case GITS_PIDR0: return 0x92; /* part number, bits[7:0] */ case GITS_PIDR1: return 0xb4; /* part number, bits[11:8] */ case GITS_PIDR2: return GIC_PIDR2_ARCH_GICv3 | 0x0b; case GITS_PIDR4: return 0x40; /* This is a 64K software visible page */ /* The following are the ID registers for (any) GIC. */ case GITS_CIDR0: return 0x0d; case GITS_CIDR1: return 0xf0; case GITS_CIDR2: return 0x05; case GITS_CIDR3: return 0xb1; } return 0; } static struct vgic_its *__vgic_doorbell_to_its(struct kvm *kvm, gpa_t db) { struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, db); if (!kvm_io_dev) return ERR_PTR(-EINVAL); if (kvm_io_dev->ops != &kvm_io_gic_ops) return ERR_PTR(-EINVAL); iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); if (iodev->iodev_type != IODEV_ITS) return ERR_PTR(-EINVAL); return iodev->its; } static unsigned long vgic_its_cache_key(u32 devid, u32 eventid) { return (((unsigned long)devid) << VITS_TYPER_IDBITS) | eventid; } static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, u32 devid, u32 eventid) { unsigned long cache_key = vgic_its_cache_key(devid, eventid); struct vgic_its *its; struct vgic_irq *irq; if (devid > VITS_MAX_DEVID || eventid > VITS_MAX_EVENTID) return NULL; its = __vgic_doorbell_to_its(kvm, db); if (IS_ERR(its)) return NULL; rcu_read_lock(); irq = xa_load(&its->translation_cache, cache_key); if (!vgic_try_get_irq_kref(irq)) irq = NULL; rcu_read_unlock(); return irq; } static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq *irq) { unsigned long cache_key = vgic_its_cache_key(devid, eventid); struct vgic_irq *old; /* Do not cache a directly injected interrupt */ if (irq->hw) return; /* * The irq refcount is guaranteed to be nonzero while holding the * its_lock, as the ITE (and the reference it holds) cannot be freed. */ lockdep_assert_held(&its->its_lock); vgic_get_irq_kref(irq); old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); /* * Put the reference taken on @irq if the store fails. Intentionally do * not return the error as the translation cache is best effort. */ if (xa_is_err(old)) { vgic_put_irq(kvm, irq); return; } /* * We could have raced with another CPU caching the same * translation behind our back, ensure we don't leak a * reference if that is the case. */ if (old) vgic_put_irq(kvm, old); } static void vgic_its_invalidate_cache(struct vgic_its *its) { struct kvm *kvm = its->dev->kvm; struct vgic_irq *irq; unsigned long idx; xa_for_each(&its->translation_cache, idx, irq) { xa_erase(&its->translation_cache, idx); vgic_put_irq(kvm, irq); } } void vgic_its_invalidate_all_caches(struct kvm *kvm) { struct kvm_device *dev; struct vgic_its *its; rcu_read_lock(); list_for_each_entry_rcu(dev, &kvm->devices, vm_node) { if (dev->ops != &kvm_arm_vgic_its_ops) continue; its = dev->private; vgic_its_invalidate_cache(its); } rcu_read_unlock(); } int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq) { struct kvm_vcpu *vcpu; struct its_ite *ite; if (!its->enabled) return -EBUSY; ite = find_ite(its, devid, eventid); if (!ite || !its_is_collection_mapped(ite->collection)) return E_ITS_INT_UNMAPPED_INTERRUPT; vcpu = collection_to_vcpu(kvm, ite->collection); if (!vcpu) return E_ITS_INT_UNMAPPED_INTERRUPT; if (!vgic_lpis_enabled(vcpu)) return -EBUSY; vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq); *irq = ite->irq; return 0; } struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi) { u64 address; if (!vgic_has_its(kvm)) return ERR_PTR(-ENODEV); if (!(msi->flags & KVM_MSI_VALID_DEVID)) return ERR_PTR(-EINVAL); address = (u64)msi->address_hi << 32 | msi->address_lo; return __vgic_doorbell_to_its(kvm, address); } /* * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. * Returns 0 on success, a positive error value for any ITS mapping * related errors and negative error values for generic errors. */ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid) { struct vgic_irq *irq = NULL; unsigned long flags; int err; err = vgic_its_resolve_lpi(kvm, its, devid, eventid, &irq); if (err) return err; if (irq->hw) return irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); return 0; } int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) { struct vgic_irq *irq; unsigned long flags; phys_addr_t db; db = (u64)msi->address_hi << 32 | msi->address_lo; irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data); if (!irq) return -EWOULDBLOCK; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); vgic_put_irq(kvm, irq); return 0; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { struct vgic_its *its; int ret; if (!vgic_its_inject_cached_translation(kvm, msi)) return 1; its = vgic_msi_to_its(kvm, msi); if (IS_ERR(its)) return PTR_ERR(its); mutex_lock(&its->its_lock); ret = vgic_its_trigger_msi(kvm, its, msi->devid, msi->data); mutex_unlock(&its->its_lock); if (ret < 0) return ret; /* * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 * if the guest has blocked the MSI. So we map any LPI mapping * related error to that. */ if (ret) return 0; else return 1; } /* Requires the its_lock to be held. */ static void its_free_ite(struct kvm *kvm, struct its_ite *ite) { list_del(&ite->ite_list); /* This put matches the get in vgic_add_lpi. */ if (ite->irq) { if (ite->irq->hw) WARN_ON(its_unmap_vlpi(ite->irq->host_irq)); vgic_put_irq(kvm, ite->irq); } kfree(ite); } static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size) { return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1); } #define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8) #define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32) #define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1) #define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32) #define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32) #define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16) #define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8) #define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32) #define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1) /* * The DISCARD command frees an Interrupt Translation Table Entry (ITTE). * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (ite && its_is_collection_mapped(ite->collection)) { struct its_device *device = find_its_device(its, device_id); int ite_esz = vgic_its_get_abi(its)->ite_esz; gpa_t gpa = device->itt_addr + ite->event_id * ite_esz; /* * Though the spec talks about removing the pending state, we * don't bother here since we clear the ITTE anyway and the * pending state is a property of the ITTE struct. */ vgic_its_invalidate_cache(its); its_free_ite(kvm, ite); return vgic_its_write_entry_lock(its, gpa, 0ULL, ite); } return E_ITS_DISCARD_UNMAPPED_INTERRUPT; } /* * The MOVI command moves an ITTE to a different collection. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); struct kvm_vcpu *vcpu; struct its_ite *ite; struct its_collection *collection; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_MOVI_UNMAPPED_INTERRUPT; if (!its_is_collection_mapped(ite->collection)) return E_ITS_MOVI_UNMAPPED_COLLECTION; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_MOVI_UNMAPPED_COLLECTION; ite->collection = collection; vcpu = collection_to_vcpu(kvm, collection); vgic_its_invalidate_cache(its); return update_affinity(ite->irq, vcpu); } static bool __is_visible_gfn_locked(struct vgic_its *its, gpa_t gpa) { gfn_t gfn = gpa >> PAGE_SHIFT; int idx; bool ret; idx = srcu_read_lock(&its->dev->kvm->srcu); ret = kvm_is_visible_gfn(its->dev->kvm, gfn); srcu_read_unlock(&its->dev->kvm->srcu, idx); return ret; } /* * Check whether an ID can be stored into the corresponding guest table. * For a direct table this is pretty easy, but gets a bit nasty for * indirect tables. We check whether the resulting guest physical address * is actually valid (covered by a memslot and guest accessible). * For this we have to read the respective first level entry. */ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, gpa_t *eaddr) { int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; u64 indirect_ptr, type = GITS_BASER_TYPE(baser); phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); int esz = GITS_BASER_ENTRY_SIZE(baser); int index; switch (type) { case GITS_BASER_TYPE_DEVICE: if (id > VITS_MAX_DEVID) return false; break; case GITS_BASER_TYPE_COLLECTION: /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */ if (id >= BIT_ULL(16)) return false; break; default: return false; } if (!(baser & GITS_BASER_INDIRECT)) { phys_addr_t addr; if (id >= (l1_tbl_size / esz)) return false; addr = base + id * esz; if (eaddr) *eaddr = addr; return __is_visible_gfn_locked(its, addr); } /* calculate and check the index into the 1st level */ index = id / (SZ_64K / esz); if (index >= (l1_tbl_size / sizeof(u64))) return false; /* Each 1st level entry is represented by a 64-bit value. */ if (kvm_read_guest_lock(its->dev->kvm, base + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; indirect_ptr = le64_to_cpu(indirect_ptr); /* check the valid bit of the first level entry */ if (!(indirect_ptr & BIT_ULL(63))) return false; /* Mask the guest physical address and calculate the frame number. */ indirect_ptr &= GENMASK_ULL(51, 16); /* Find the address of the actual entry */ index = id % (SZ_64K / esz); indirect_ptr += index * esz; if (eaddr) *eaddr = indirect_ptr; return __is_visible_gfn_locked(its, indirect_ptr); } /* * Check whether an event ID can be stored in the corresponding Interrupt * Translation Table, which starts at device->itt_addr. */ static bool vgic_its_check_event_id(struct vgic_its *its, struct its_device *device, u32 event_id) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int ite_esz = abi->ite_esz; gpa_t gpa; /* max table size is: BIT_ULL(device->num_eventid_bits) * ite_esz */ if (event_id >= BIT_ULL(device->num_eventid_bits)) return false; gpa = device->itt_addr + event_id * ite_esz; return __is_visible_gfn_locked(its, gpa); } /* * Add a new collection into the ITS collection table. * Returns 0 on success, and a negative error value for generic errors. */ static int vgic_its_alloc_collection(struct vgic_its *its, struct its_collection **colp, u32 coll_id) { struct its_collection *collection; collection = kzalloc(sizeof(*collection), GFP_KERNEL_ACCOUNT); if (!collection) return -ENOMEM; collection->collection_id = coll_id; collection->target_addr = COLLECTION_NOT_MAPPED; list_add_tail(&collection->coll_list, &its->collection_list); *colp = collection; return 0; } static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id) { struct its_collection *collection; struct its_device *device; struct its_ite *ite; /* * Clearing the mapping for that collection ID removes the * entry from the list. If there wasn't any before, we can * go home early. */ collection = find_collection(its, coll_id); if (!collection) return; for_each_lpi_its(device, ite, its) if (ite->collection && ite->collection->collection_id == coll_id) ite->collection = NULL; list_del(&collection->coll_list); kfree(collection); } /* Must be called with its_lock mutex held */ static struct its_ite *vgic_its_alloc_ite(struct its_device *device, struct its_collection *collection, u32 event_id) { struct its_ite *ite; ite = kzalloc(sizeof(*ite), GFP_KERNEL_ACCOUNT); if (!ite) return ERR_PTR(-ENOMEM); ite->event_id = event_id; ite->collection = collection; list_add_tail(&ite->ite_list, &device->itt_head); return ite; } /* * The MAPTI and MAPI commands map LPIs to ITTEs. * Must be called with its_lock mutex held. */ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); u32 coll_id = its_cmd_get_collection(its_cmd); struct its_ite *ite; struct kvm_vcpu *vcpu = NULL; struct its_device *device; struct its_collection *collection, *new_coll = NULL; struct vgic_irq *irq; int lpi_nr; device = find_its_device(its, device_id); if (!device) return E_ITS_MAPTI_UNMAPPED_DEVICE; if (!vgic_its_check_event_id(its, device, event_id)) return E_ITS_MAPTI_ID_OOR; if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI) lpi_nr = its_cmd_get_physical_id(its_cmd); else lpi_nr = event_id; if (lpi_nr < GIC_LPI_OFFSET || lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; /* If there is an existing mapping, behavior is UNPREDICTABLE. */ if (find_ite(its, device_id, event_id)) return 0; collection = find_collection(its, coll_id); if (!collection) { int ret; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return E_ITS_MAPC_COLLECTION_OOR; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; new_coll = collection; } ite = vgic_its_alloc_ite(device, collection, event_id); if (IS_ERR(ite)) { if (new_coll) vgic_its_free_collection(its, coll_id); return PTR_ERR(ite); } if (its_is_collection_mapped(collection)) vcpu = collection_to_vcpu(kvm, collection); irq = vgic_add_lpi(kvm, lpi_nr, vcpu); if (IS_ERR(irq)) { if (new_coll) vgic_its_free_collection(its, coll_id); its_free_ite(kvm, ite); return PTR_ERR(irq); } ite->irq = irq; return 0; } /* Requires the its_lock to be held. */ static void vgic_its_free_device(struct kvm *kvm, struct vgic_its *its, struct its_device *device) { struct its_ite *ite, *temp; /* * The spec says that unmapping a device with still valid * ITTEs associated is UNPREDICTABLE. We remove all ITTEs, * since we cannot leave the memory unreferenced. */ list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list) its_free_ite(kvm, ite); vgic_its_invalidate_cache(its); list_del(&device->dev_list); kfree(device); } /* its lock must be held */ static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its) { struct its_device *cur, *temp; list_for_each_entry_safe(cur, temp, &its->device_list, dev_list) vgic_its_free_device(kvm, its, cur); } /* its lock must be held */ static void vgic_its_free_collection_list(struct kvm *kvm, struct vgic_its *its) { struct its_collection *cur, *temp; list_for_each_entry_safe(cur, temp, &its->collection_list, coll_list) vgic_its_free_collection(its, cur->collection_id); } /* Must be called with its_lock mutex held */ static struct its_device *vgic_its_alloc_device(struct vgic_its *its, u32 device_id, gpa_t itt_addr, u8 num_eventid_bits) { struct its_device *device; device = kzalloc(sizeof(*device), GFP_KERNEL_ACCOUNT); if (!device) return ERR_PTR(-ENOMEM); device->device_id = device_id; device->itt_addr = itt_addr; device->num_eventid_bits = num_eventid_bits; INIT_LIST_HEAD(&device->itt_head); list_add_tail(&device->dev_list, &its->device_list); return device; } /* * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs). * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); bool valid = its_cmd_get_validbit(its_cmd); u8 num_eventid_bits = its_cmd_get_size(its_cmd); gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd); struct its_device *device; gpa_t gpa; if (!vgic_its_check_id(its, its->baser_device_table, device_id, &gpa)) return E_ITS_MAPD_DEVICE_OOR; if (valid && num_eventid_bits > VITS_TYPER_IDBITS) return E_ITS_MAPD_ITTSIZE_OOR; device = find_its_device(its, device_id); /* * The spec says that calling MAPD on an already mapped device * invalidates all cached data for this device. We implement this * by removing the mapping and re-establishing it. */ if (device) vgic_its_free_device(kvm, its, device); /* * The spec does not say whether unmapping a not-mapped device * is an error, so we are done in any case. */ if (!valid) return vgic_its_write_entry_lock(its, gpa, 0ULL, dte); device = vgic_its_alloc_device(its, device_id, itt_addr, num_eventid_bits); return PTR_ERR_OR_ZERO(device); } /* * The MAPC command maps collection IDs to redistributors. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u16 coll_id; struct its_collection *collection; bool valid; valid = its_cmd_get_validbit(its_cmd); coll_id = its_cmd_get_collection(its_cmd); if (!valid) { vgic_its_free_collection(its, coll_id); vgic_its_invalidate_cache(its); } else { struct kvm_vcpu *vcpu; vcpu = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd)); if (!vcpu) return E_ITS_MAPC_PROCNUM_OOR; collection = find_collection(its, coll_id); if (!collection) { int ret; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return E_ITS_MAPC_COLLECTION_OOR; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; collection->target_addr = vcpu->vcpu_id; } else { collection->target_addr = vcpu->vcpu_id; update_affinity_collection(kvm, its, collection); } } return 0; } /* * The CLEAR command removes the pending state for a particular LPI. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_CLEAR_UNMAPPED_INTERRUPT; ite->irq->pending_latch = false; if (ite->irq->hw) return irq_set_irqchip_state(ite->irq->host_irq, IRQCHIP_STATE_PENDING, false); return 0; } int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq) { return update_lpi_config(kvm, irq, NULL, true); } /* * The INV command syncs the configuration bits from the memory table. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 device_id = its_cmd_get_deviceid(its_cmd); u32 event_id = its_cmd_get_id(its_cmd); struct its_ite *ite; ite = find_ite(its, device_id, event_id); if (!ite) return E_ITS_INV_UNMAPPED_INTERRUPT; return vgic_its_inv_lpi(kvm, ite->irq); } /** * vgic_its_invall - invalidate all LPIs targeting a given vcpu * @vcpu: the vcpu for which the RD is targeted by an invalidation * * Contrary to the INVALL command, this targets a RD instead of a * collection, and we don't need to hold the its_lock, since no ITS is * involved here. */ int vgic_its_invall(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; xa_for_each(&dist->lpi_xa, intid, irq) { irq = vgic_get_irq(kvm, intid); if (!irq) continue; update_lpi_config(kvm, irq, vcpu, false); vgic_put_irq(kvm, irq); } if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); return 0; } /* * The INVALL command requests flushing of all IRQ data in this collection. * Find the VCPU mapped to that collection, then iterate over the VM's list * of mapped LPIs and update the configuration for each IRQ which targets * the specified vcpu. The configuration will be read from the in-memory * configuration table. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 coll_id = its_cmd_get_collection(its_cmd); struct its_collection *collection; struct kvm_vcpu *vcpu; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_INVALL_UNMAPPED_COLLECTION; vcpu = collection_to_vcpu(kvm, collection); vgic_its_invall(vcpu); return 0; } /* * The MOVALL command moves the pending state of all IRQs targeting one * redistributor to another. We don't hold the pending state in the VCPUs, * but in the IRQs instead, so there is really not much to do for us here. * However the spec says that no IRQ must target the old redistributor * afterwards, so we make sure that no LPI is using the associated target_vcpu. * This command affects all LPIs in the system that target that redistributor. */ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu1, *vcpu2; struct vgic_irq *irq; unsigned long intid; /* We advertise GITS_TYPER.PTA==0, making the address the vcpu ID */ vcpu1 = kvm_get_vcpu_by_id(kvm, its_cmd_get_target_addr(its_cmd)); vcpu2 = kvm_get_vcpu_by_id(kvm, its_cmd_mask_field(its_cmd, 3, 16, 32)); if (!vcpu1 || !vcpu2) return E_ITS_MOVALL_PROCNUM_OOR; if (vcpu1 == vcpu2) return 0; xa_for_each(&dist->lpi_xa, intid, irq) { irq = vgic_get_irq(kvm, intid); if (!irq) continue; update_affinity(irq, vcpu2); vgic_put_irq(kvm, irq); } vgic_its_invalidate_cache(its); return 0; } /* * The INT command injects the LPI associated with that DevID/EvID pair. * Must be called with the its_lock mutex held. */ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* * This function is called with the its_cmd lock held, but the ITS data * structure lock dropped. */ static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its, u64 *its_cmd) { int ret = -ENODEV; mutex_lock(&its->its_lock); switch (its_cmd_get_command(its_cmd)) { case GITS_CMD_MAPD: ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd); break; case GITS_CMD_MAPC: ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd); break; case GITS_CMD_MAPI: ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); break; case GITS_CMD_MAPTI: ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); break; case GITS_CMD_MOVI: ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd); break; case GITS_CMD_DISCARD: ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd); break; case GITS_CMD_CLEAR: ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd); break; case GITS_CMD_MOVALL: ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd); break; case GITS_CMD_INT: ret = vgic_its_cmd_handle_int(kvm, its, its_cmd); break; case GITS_CMD_INV: ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd); break; case GITS_CMD_INVALL: ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd); break; case GITS_CMD_SYNC: /* we ignore this command: we are in sync all of the time */ ret = 0; break; } mutex_unlock(&its->its_lock); return ret; } static u64 vgic_sanitise_its_baser(u64 reg) { reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK, GITS_BASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK, GITS_BASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK, GITS_BASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); /* We support only one (ITS) page size: 64K */ reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K; return reg; } static u64 vgic_sanitise_its_cbaser(u64 reg) { reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK, GITS_CBASER_SHAREABILITY_SHIFT, vgic_sanitise_shareability); reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK, GITS_CBASER_INNER_CACHEABILITY_SHIFT, vgic_sanitise_inner_cacheability); reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK, GITS_CBASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); /* Sanitise the physical address to be 64k aligned. */ reg &= ~GENMASK_ULL(15, 12); return reg; } static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->cbaser, addr & 7, len); } static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { /* When GITS_CTLR.Enable is 1, this register is RO. */ if (its->enabled) return; mutex_lock(&its->cmd_lock); its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val); its->cbaser = vgic_sanitise_its_cbaser(its->cbaser); its->creadr = 0; /* * CWRITER is architecturally UNKNOWN on reset, but we need to reset * it to CREADR to make sure we start with an empty command buffer. */ its->cwriter = its->creadr; mutex_unlock(&its->cmd_lock); } #define ITS_CMD_BUFFER_SIZE(baser) ((((baser) & 0xff) + 1) << 12) #define ITS_CMD_SIZE 32 #define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5)) /* Must be called with the cmd_lock held. */ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) { gpa_t cbaser; u64 cmd_buf[4]; /* Commands are only processed when the ITS is enabled. */ if (!its->enabled) return; cbaser = GITS_CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, cmd_buf, ITS_CMD_SIZE); /* * If kvm_read_guest() fails, this could be due to the guest * programming a bogus value in CBASER or something else going * wrong from which we cannot easily recover. * According to section 6.3.2 in the GICv3 spec we can just * ignore that command then. */ if (!ret) vgic_its_handle_command(kvm, its, cmd_buf); its->creadr += ITS_CMD_SIZE; if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser)) its->creadr = 0; } } /* * By writing to CWRITER the guest announces new commands to be processed. * To avoid any races in the first place, we take the its_cmd lock, which * protects our ring buffer variables, so that there is only one user * per ITS handling commands at a given time. */ static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u64 reg; if (!its) return; mutex_lock(&its->cmd_lock); reg = update_64bit_reg(its->cwriter, addr & 7, len, val); reg = ITS_CMD_OFFSET(reg); if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { mutex_unlock(&its->cmd_lock); return; } its->cwriter = reg; vgic_its_process_commands(kvm, its); mutex_unlock(&its->cmd_lock); } static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->cwriter, addr & 0x7, len); } static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { return extract_bytes(its->creadr, addr & 0x7, len); } static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { u32 cmd_offset; int ret = 0; mutex_lock(&its->cmd_lock); if (its->enabled) { ret = -EBUSY; goto out; } cmd_offset = ITS_CMD_OFFSET(val); if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { ret = -EINVAL; goto out; } its->creadr = cmd_offset; out: mutex_unlock(&its->cmd_lock); return ret; } #define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7) static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len) { u64 reg; switch (BASER_INDEX(addr)) { case 0: reg = its->baser_device_table; break; case 1: reg = its->baser_coll_table; break; default: reg = 0; break; } return extract_bytes(reg, addr & 7, len); } #define GITS_BASER_RO_MASK (GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56)) static void vgic_mmio_write_its_baser(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 entry_size, table_type; u64 reg, *regptr, clearbits = 0; /* When GITS_CTLR.Enable is 1, we ignore write accesses. */ if (its->enabled) return; switch (BASER_INDEX(addr)) { case 0: regptr = &its->baser_device_table; entry_size = abi->dte_esz; table_type = GITS_BASER_TYPE_DEVICE; break; case 1: regptr = &its->baser_coll_table; entry_size = abi->cte_esz; table_type = GITS_BASER_TYPE_COLLECTION; clearbits = GITS_BASER_INDIRECT; break; default: return; } reg = update_64bit_reg(*regptr, addr & 7, len, val); reg &= ~GITS_BASER_RO_MASK; reg &= ~clearbits; reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT; reg |= table_type << GITS_BASER_TYPE_SHIFT; reg = vgic_sanitise_its_baser(reg); *regptr = reg; if (!(reg & GITS_BASER_VALID)) { /* Take the its_lock to prevent a race with a save/restore */ mutex_lock(&its->its_lock); switch (table_type) { case GITS_BASER_TYPE_DEVICE: vgic_its_free_device_list(kvm, its); break; case GITS_BASER_TYPE_COLLECTION: vgic_its_free_collection_list(kvm, its); break; } mutex_unlock(&its->its_lock); } } static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, struct vgic_its *its, gpa_t addr, unsigned int len) { u32 reg = 0; mutex_lock(&its->cmd_lock); if (its->creadr == its->cwriter) reg |= GITS_CTLR_QUIESCENT; if (its->enabled) reg |= GITS_CTLR_ENABLE; mutex_unlock(&its->cmd_lock); return reg; } static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { mutex_lock(&its->cmd_lock); /* * It is UNPREDICTABLE to enable the ITS if any of the CBASER or * device/collection BASER are invalid */ if (!its->enabled && (val & GITS_CTLR_ENABLE) && (!(its->baser_device_table & GITS_BASER_VALID) || !(its->baser_coll_table & GITS_BASER_VALID) || !(its->cbaser & GITS_CBASER_VALID))) goto out; its->enabled = !!(val & GITS_CTLR_ENABLE); if (!its->enabled) vgic_its_invalidate_cache(its); /* * Try to process any pending commands. This function bails out early * if the ITS is disabled or no commands have been queued. */ vgic_its_process_commands(kvm, its); out: mutex_unlock(&its->cmd_lock); } #define REGISTER_ITS_DESC(off, rd, wr, length, acc) \ { \ .reg_offset = off, \ .len = length, \ .access_flags = acc, \ .its_read = rd, \ .its_write = wr, \ } #define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\ { \ .reg_offset = off, \ .len = length, \ .access_flags = acc, \ .its_read = rd, \ .its_write = wr, \ .uaccess_its_write = uwr, \ } static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ } static struct vgic_register_region its_registers[] = { REGISTER_ITS_DESC(GITS_CTLR, vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4, VGIC_ACCESS_32bit), REGISTER_ITS_DESC_UACCESS(GITS_IIDR, vgic_mmio_read_its_iidr, its_mmio_write_wi, vgic_mmio_uaccess_write_its_iidr, 4, VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_TYPER, vgic_mmio_read_its_typer, its_mmio_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_CBASER, vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_CWRITER, vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC_UACCESS(GITS_CREADR, vgic_mmio_read_its_creadr, its_mmio_write_wi, vgic_mmio_uaccess_write_its_creadr, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_BASER, vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_ITS_DESC(GITS_IDREGS_BASE, vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30, VGIC_ACCESS_32bit), }; /* This is called on setting the LPI enable bit in the redistributor. */ void vgic_enable_lpis(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ)) its_sync_lpi_pending_table(vcpu); } static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its, u64 addr) { struct vgic_io_device *iodev = &its->iodev; int ret; mutex_lock(&kvm->slots_lock); if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -EBUSY; goto out; } its->vgic_its_base = addr; iodev->regions = its_registers; iodev->nr_regions = ARRAY_SIZE(its_registers); kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops); iodev->base_addr = its->vgic_its_base; iodev->iodev_type = IODEV_ITS; iodev->its = its; ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr, KVM_VGIC_V3_ITS_SIZE, &iodev->dev); out: mutex_unlock(&kvm->slots_lock); return ret; } #define INITIAL_BASER_VALUE \ (GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \ GITS_BASER_PAGE_SIZE_64K) #define INITIAL_PROPBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)) static int vgic_its_create(struct kvm_device *dev, u32 type) { int ret; struct vgic_its *its; if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) return -ENODEV; its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL_ACCOUNT); if (!its) return -ENOMEM; mutex_lock(&dev->kvm->arch.config_lock); if (vgic_initialized(dev->kvm)) { ret = vgic_v4_init(dev->kvm); if (ret < 0) { mutex_unlock(&dev->kvm->arch.config_lock); kfree(its); return ret; } } mutex_init(&its->its_lock); mutex_init(&its->cmd_lock); /* Yep, even more trickery for lock ordering... */ #ifdef CONFIG_LOCKDEP mutex_lock(&its->cmd_lock); mutex_lock(&its->its_lock); mutex_unlock(&its->its_lock); mutex_unlock(&its->cmd_lock); #endif its->vgic_its_base = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&its->device_list); INIT_LIST_HEAD(&its->collection_list); xa_init(&its->translation_cache); dev->kvm->arch.vgic.msis_require_devid = true; dev->kvm->arch.vgic.has_its = true; its->enabled = false; its->dev = dev; its->baser_device_table = INITIAL_BASER_VALUE | ((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT); its->baser_coll_table = INITIAL_BASER_VALUE | ((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT); dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE; dev->private = its; ret = vgic_its_set_abi(its, NR_ITS_ABIS - 1); mutex_unlock(&dev->kvm->arch.config_lock); return ret; } static void vgic_its_destroy(struct kvm_device *kvm_dev) { struct kvm *kvm = kvm_dev->kvm; struct vgic_its *its = kvm_dev->private; mutex_lock(&its->its_lock); vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); vgic_its_invalidate_cache(its); xa_destroy(&its->translation_cache); mutex_unlock(&its->its_lock); kfree(its); kfree(kvm_dev);/* alloc by kvm_ioctl_create_device, free by .destroy */ } static int vgic_its_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) { const struct vgic_register_region *region; gpa_t offset = attr->attr; int align; align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7; if (offset & align) return -EINVAL; region = vgic_find_mmio_region(its_registers, ARRAY_SIZE(its_registers), offset); if (!region) return -ENXIO; return 0; } static int vgic_its_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, u64 *reg, bool is_write) { const struct vgic_register_region *region; struct vgic_its *its; gpa_t addr, offset; unsigned int len; int align, ret = 0; its = dev->private; offset = attr->attr; /* * Although the spec supports upper/lower 32-bit accesses to * 64-bit ITS registers, the userspace ABI requires 64-bit * accesses to all 64-bit wide registers. We therefore only * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID * registers */ if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4)) align = 0x3; else align = 0x7; if (offset & align) return -EINVAL; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -ENXIO; goto out; } region = vgic_find_mmio_region(its_registers, ARRAY_SIZE(its_registers), offset); if (!region) { ret = -ENXIO; goto out; } addr = its->vgic_its_base + offset; len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; if (is_write) { if (region->uaccess_its_write) ret = region->uaccess_its_write(dev->kvm, its, addr, len, *reg); else region->its_write(dev->kvm, its, addr, len, *reg); } else { *reg = region->its_read(dev->kvm, its, addr, len); } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return ret; } static u32 compute_next_devid_offset(struct list_head *h, struct its_device *dev) { struct its_device *next; u32 next_offset; if (list_is_last(&dev->dev_list, h)) return 0; next = list_next_entry(dev, dev_list); next_offset = next->device_id - dev->device_id; return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET); } static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite) { struct its_ite *next; u32 next_offset; if (list_is_last(&ite->ite_list, h)) return 0; next = list_next_entry(ite, ite_list); next_offset = next->event_id - ite->event_id; return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET); } /** * typedef entry_fn_t - Callback called on a table entry restore path * @its: its handle * @id: id of the entry * @entry: pointer to the entry * @opaque: pointer to an opaque data * * Return: < 0 on error, 0 if last element was identified, id offset to next * element otherwise */ typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, void *opaque); /** * scan_its_table - Scan a contiguous table in guest RAM and applies a function * to each entry * * @its: its handle * @base: base gpa of the table * @size: size of the table in bytes * @esz: entry size in bytes * @start_id: the ID of the first entry in the table * (non zero for 2d level tables) * @fn: function to apply on each entry * @opaque: pointer to opaque data * * Return: < 0 on error, 0 if last element was identified, 1 otherwise * (the last element may not be found on second level tables) */ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, int start_id, entry_fn_t fn, void *opaque) { struct kvm *kvm = its->dev->kvm; unsigned long len = size; int id = start_id; gpa_t gpa = base; char entry[ESZ_MAX]; int ret; memset(entry, 0, esz); while (true) { int next_offset; size_t byte_offset; ret = kvm_read_guest_lock(kvm, gpa, entry, esz); if (ret) return ret; next_offset = fn(its, id, entry, opaque); if (next_offset <= 0) return next_offset; byte_offset = next_offset * esz; if (byte_offset >= len) break; id += next_offset; gpa += byte_offset; len -= byte_offset; } return 1; } /* * vgic_its_save_ite - Save an interrupt translation entry at @gpa */ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, struct its_ite *ite, gpa_t gpa) { u32 next_offset; u64 val; next_offset = compute_next_eventid_offset(&dev->itt_head, ite); val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) | ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); return vgic_its_write_entry_lock(its, gpa, val, ite); } /** * vgic_its_restore_ite - restore an interrupt translation entry * * @its: its handle * @event_id: id used for indexing * @ptr: pointer to the ITE entry * @opaque: pointer to the its_device */ static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, void *ptr, void *opaque) { struct its_device *dev = opaque; struct its_collection *collection; struct kvm *kvm = its->dev->kvm; struct kvm_vcpu *vcpu = NULL; u64 val; u64 *p = (u64 *)ptr; struct vgic_irq *irq; u32 coll_id, lpi_id; struct its_ite *ite; u32 offset; val = *p; val = le64_to_cpu(val); coll_id = val & KVM_ITS_ITE_ICID_MASK; lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT; if (!lpi_id) return 1; /* invalid entry, no choice but to scan next entry */ if (lpi_id < VGIC_MIN_LPI) return -EINVAL; offset = val >> KVM_ITS_ITE_NEXT_SHIFT; if (event_id + offset >= BIT_ULL(dev->num_eventid_bits)) return -EINVAL; collection = find_collection(its, coll_id); if (!collection) return -EINVAL; if (!vgic_its_check_event_id(its, dev, event_id)) return -EINVAL; ite = vgic_its_alloc_ite(dev, collection, event_id); if (IS_ERR(ite)) return PTR_ERR(ite); if (its_is_collection_mapped(collection)) vcpu = kvm_get_vcpu_by_id(kvm, collection->target_addr); irq = vgic_add_lpi(kvm, lpi_id, vcpu); if (IS_ERR(irq)) { its_free_ite(kvm, ite); return PTR_ERR(irq); } ite->irq = irq; return offset; } static int vgic_its_ite_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct its_ite *itea = container_of(a, struct its_ite, ite_list); struct its_ite *iteb = container_of(b, struct its_ite, ite_list); if (itea->event_id < iteb->event_id) return -1; else return 1; } static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); gpa_t base = device->itt_addr; struct its_ite *ite; int ret; int ite_esz = abi->ite_esz; list_sort(NULL, &device->itt_head, vgic_its_ite_cmp); list_for_each_entry(ite, &device->itt_head, ite_list) { gpa_t gpa = base + ite->event_id * ite_esz; /* * If an LPI carries the HW bit, this means that this * interrupt is controlled by GICv4, and we do not * have direct access to that state without GICv4.1. * Let's simply fail the save operation... */ if (ite->irq->hw && !kvm_vgic_global_state.has_gicv4_1) return -EACCES; ret = vgic_its_save_ite(its, device, ite, gpa); if (ret) return ret; } return 0; } /** * vgic_its_restore_itt - restore the ITT of a device * * @its: its handle * @dev: device handle * * Return 0 on success, < 0 on error */ static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); gpa_t base = dev->itt_addr; int ret; int ite_esz = abi->ite_esz; size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz; ret = scan_its_table(its, base, max_size, ite_esz, 0, vgic_its_restore_ite, dev); /* scan_its_table returns +1 if all ITEs are invalid */ if (ret > 0) ret = 0; return ret; } /** * vgic_its_save_dte - Save a device table entry at a given GPA * * @its: ITS handle * @dev: ITS device * @ptr: GPA */ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, gpa_t ptr) { u64 val, itt_addr_field; u32 next_offset; itt_addr_field = dev->itt_addr >> 8; next_offset = compute_next_devid_offset(&its->device_list, dev); val = (1ULL << KVM_ITS_DTE_VALID_SHIFT | ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) | (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); return vgic_its_write_entry_lock(its, ptr, val, dte); } /** * vgic_its_restore_dte - restore a device table entry * * @its: its handle * @id: device id the DTE corresponds to * @ptr: kernel VA where the 8 byte DTE is located * @opaque: unused * * Return: < 0 on error, 0 if the dte is the last one, id offset to the * next dte otherwise */ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, void *ptr, void *opaque) { struct its_device *dev; u64 baser = its->baser_device_table; gpa_t itt_addr; u8 num_eventid_bits; u64 entry = *(u64 *)ptr; bool valid; u32 offset; int ret; entry = le64_to_cpu(entry); valid = entry >> KVM_ITS_DTE_VALID_SHIFT; num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1; itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK) >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8; if (!valid) return 1; /* dte entry is valid */ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; if (!vgic_its_check_id(its, baser, id, NULL)) return -EINVAL; dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits); if (IS_ERR(dev)) return PTR_ERR(dev); ret = vgic_its_restore_itt(its, dev); if (ret) { vgic_its_free_device(its->dev->kvm, its, dev); return ret; } return offset; } static int vgic_its_device_cmp(void *priv, const struct list_head *a, const struct list_head *b) { struct its_device *deva = container_of(a, struct its_device, dev_list); struct its_device *devb = container_of(b, struct its_device, dev_list); if (deva->device_id < devb->device_id) return -1; else return 1; } /* * vgic_its_save_device_tables - Save the device table and all ITT * into guest RAM * * L1/L2 handling is hidden by vgic_its_check_id() helper which directly * returns the GPA of the device entry */ static int vgic_its_save_device_tables(struct vgic_its *its) { u64 baser = its->baser_device_table; struct its_device *dev; if (!(baser & GITS_BASER_VALID)) return 0; list_sort(NULL, &its->device_list, vgic_its_device_cmp); list_for_each_entry(dev, &its->device_list, dev_list) { int ret; gpa_t eaddr; if (!vgic_its_check_id(its, baser, dev->device_id, &eaddr)) return -EINVAL; ret = vgic_its_save_itt(its, dev); if (ret) return ret; ret = vgic_its_save_dte(its, dev, eaddr); if (ret) return ret; } return 0; } /** * handle_l1_dte - callback used for L1 device table entries (2 stage case) * * @its: its handle * @id: index of the entry in the L1 table * @addr: kernel VA * @opaque: unused * * L1 table entries are scanned by steps of 1 entry * Return < 0 if error, 0 if last dte was found when scanning the L2 * table, +1 otherwise (meaning next L1 entry must be scanned) */ static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, void *opaque) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int l2_start_id = id * (SZ_64K / abi->dte_esz); u64 entry = *(u64 *)addr; int dte_esz = abi->dte_esz; gpa_t gpa; int ret; entry = le64_to_cpu(entry); if (!(entry & KVM_ITS_L1E_VALID_MASK)) return 1; gpa = entry & KVM_ITS_L1E_ADDR_MASK; ret = scan_its_table(its, gpa, SZ_64K, dte_esz, l2_start_id, vgic_its_restore_dte, NULL); return ret; } /* * vgic_its_restore_device_tables - Restore the device table and all ITT * from guest RAM to internal data structs */ static int vgic_its_restore_device_tables(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_device_table; int l1_esz, ret; int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; gpa_t l1_gpa; if (!(baser & GITS_BASER_VALID)) return 0; l1_gpa = GITS_BASER_ADDR_48_to_52(baser); if (baser & GITS_BASER_INDIRECT) { l1_esz = GITS_LVL1_ENTRY_SIZE; ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, handle_l1_dte, NULL); } else { l1_esz = abi->dte_esz; ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, vgic_its_restore_dte, NULL); } /* scan_its_table returns +1 if all entries are invalid */ if (ret > 0) ret = 0; if (ret < 0) vgic_its_free_device_list(its->dev->kvm, its); return ret; } static int vgic_its_save_cte(struct vgic_its *its, struct its_collection *collection, gpa_t gpa) { u64 val; val = (1ULL << KVM_ITS_CTE_VALID_SHIFT | ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); return vgic_its_write_entry_lock(its, gpa, val, cte); } /* * Restore a collection entry into the ITS collection table. * Return +1 on success, 0 if the entry was invalid (which should be * interpreted as end-of-table), and a negative error value for generic errors. */ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa) { struct its_collection *collection; struct kvm *kvm = its->dev->kvm; u32 target_addr, coll_id; u64 val; int ret; ret = vgic_its_read_entry_lock(its, gpa, &val, cte); if (ret) return ret; val = le64_to_cpu(val); if (!(val & KVM_ITS_CTE_VALID_MASK)) return 0; target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT); coll_id = val & KVM_ITS_CTE_ICID_MASK; if (target_addr != COLLECTION_NOT_MAPPED && !kvm_get_vcpu_by_id(kvm, target_addr)) return -EINVAL; collection = find_collection(its, coll_id); if (collection) return -EEXIST; if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) return -EINVAL; ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; collection->target_addr = target_addr; return 1; } /* * vgic_its_save_collection_table - Save the collection table into * guest RAM */ static int vgic_its_save_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser); struct its_collection *collection; size_t max_size, filled = 0; int ret, cte_esz = abi->cte_esz; if (!(baser & GITS_BASER_VALID)) return 0; max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; list_for_each_entry(collection, &its->collection_list, coll_list) { ret = vgic_its_save_cte(its, collection, gpa); if (ret) return ret; gpa += cte_esz; filled += cte_esz; } if (filled == max_size) return 0; /* * table is not fully filled, add a last dummy element * with valid bit unset */ return vgic_its_write_entry_lock(its, gpa, 0ULL, cte); } /* * vgic_its_restore_collection_table - reads the collection table * in guest memory and restores the ITS internal state. Requires the * BASER registers to be restored before. */ static int vgic_its_restore_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; int cte_esz = abi->cte_esz; size_t max_size, read = 0; gpa_t gpa; int ret; if (!(baser & GITS_BASER_VALID)) return 0; gpa = GITS_BASER_ADDR_48_to_52(baser); max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; while (read < max_size) { ret = vgic_its_restore_cte(its, gpa); if (ret <= 0) break; gpa += cte_esz; read += cte_esz; } if (ret > 0) return 0; if (ret < 0) vgic_its_free_collection_list(its->dev->kvm, its); return ret; } /* * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM * according to v0 ABI */ static int vgic_its_save_tables_v0(struct vgic_its *its) { int ret; ret = vgic_its_save_device_tables(its); if (ret) return ret; return vgic_its_save_collection_table(its); } /* * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM * to internal data structs according to V0 ABI * */ static int vgic_its_restore_tables_v0(struct vgic_its *its) { int ret; ret = vgic_its_restore_collection_table(its); if (ret) return ret; ret = vgic_its_restore_device_tables(its); if (ret) vgic_its_free_collection_list(its->dev->kvm, its); return ret; } static int vgic_its_commit_v0(struct vgic_its *its) { const struct vgic_its_abi *abi; abi = vgic_its_get_abi(its); its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK; its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK; its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5) << GITS_BASER_ENTRY_SIZE_SHIFT); its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5) << GITS_BASER_ENTRY_SIZE_SHIFT); return 0; } static void vgic_its_reset(struct kvm *kvm, struct vgic_its *its) { /* We need to keep the ABI specific field values */ its->baser_coll_table &= ~GITS_BASER_VALID; its->baser_device_table &= ~GITS_BASER_VALID; its->cbaser = 0; its->creadr = 0; its->cwriter = 0; its->enabled = 0; vgic_its_free_device_list(kvm, its); vgic_its_free_collection_list(kvm, its); } static int vgic_its_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_ITS_ADDR_TYPE: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_ITS_CTRL_RESET: return 0; case KVM_DEV_ARM_ITS_SAVE_TABLES: return 0; case KVM_DEV_ARM_ITS_RESTORE_TABLES: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: return vgic_its_has_attr_regs(dev, attr); } return -ENXIO; } static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ return 0; mutex_lock(&kvm->lock); if (!lock_all_vcpus(kvm)) { mutex_unlock(&kvm->lock); return -EBUSY; } mutex_lock(&kvm->arch.config_lock); mutex_lock(&its->its_lock); switch (attr) { case KVM_DEV_ARM_ITS_CTRL_RESET: vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: ret = abi->save_tables(its); break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); break; } mutex_unlock(&its->its_lock); mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); mutex_unlock(&kvm->lock); return ret; } /* * kvm_arch_allow_write_without_running_vcpu - allow writing guest memory * without the running VCPU when dirty ring is enabled. * * The running VCPU is required to track dirty guest pages when dirty ring * is enabled. Otherwise, the backup bitmap should be used to track the * dirty guest pages. When vgic/its tables are being saved, the backup * bitmap is used to track the dirty guest pages due to the missed running * VCPU in the period. */ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { struct vgic_its *its = dev->private; int ret; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; unsigned long type = (unsigned long)attr->attr; u64 addr; if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; ret = vgic_check_iorange(dev->kvm, its->vgic_its_base, addr, SZ_64K, KVM_VGIC_V3_ITS_SIZE); if (ret) return ret; return vgic_register_its_iodev(dev->kvm, its, addr); } case KVM_DEV_ARM_VGIC_GRP_CTRL: return vgic_its_ctrl(dev->kvm, its, attr->attr); case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; u64 reg; if (get_user(reg, uaddr)) return -EFAULT; return vgic_its_attr_regs_access(dev, attr, ®, true); } } return -ENXIO; } static int vgic_its_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: { struct vgic_its *its = dev->private; u64 addr = its->vgic_its_base; u64 __user *uaddr = (u64 __user *)(long)attr->addr; unsigned long type = (unsigned long)attr->attr; if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; if (copy_to_user(uaddr, &addr, sizeof(addr))) return -EFAULT; break; } case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { u64 __user *uaddr = (u64 __user *)(long)attr->addr; u64 reg; int ret; ret = vgic_its_attr_regs_access(dev, attr, ®, false); if (ret) return ret; return put_user(reg, uaddr); } default: return -ENXIO; } return 0; } static struct kvm_device_ops kvm_arm_vgic_its_ops = { .name = "kvm-arm-vgic-its", .create = vgic_its_create, .destroy = vgic_its_destroy, .set_attr = vgic_its_set_attr, .get_attr = vgic_its_get_attr, .has_attr = vgic_its_has_attr, }; int kvm_vgic_register_its_device(void) { return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } |
| 260 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM capability #if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CAPABILITY_H #include <linux/cred.h> #include <linux/tracepoint.h> #include <linux/user_namespace.h> /** * cap_capable - called after it's determined if a task has a particular * effective capability * * @cred: The credentials used * @target_ns: The user namespace of the resource being accessed * @capable_ns: The user namespace in which the credential provides the * capability to access the targeted resource. * This will be NULL if ret is not 0. * @cap: The capability to check for * @ret: The return value of the check: 0 if it does, -ve if it does not * * Allows to trace calls to cap_capable in commoncap.c */ TRACE_EVENT(cap_capable, TP_PROTO(const struct cred *cred, struct user_namespace *target_ns, const struct user_namespace *capable_ns, int cap, int ret), TP_ARGS(cred, target_ns, capable_ns, cap, ret), TP_STRUCT__entry( __field(const struct cred *, cred) __field(struct user_namespace *, target_ns) __field(const struct user_namespace *, capable_ns) __field(int, cap) __field(int, ret) ), TP_fast_assign( __entry->cred = cred; __entry->target_ns = target_ns; __entry->capable_ns = ret == 0 ? capable_ns : NULL; __entry->cap = cap; __entry->ret = ret; ), TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d", __entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap, __entry->ret) ); #endif /* _TRACE_CAPABILITY_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 9 5 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 | // SPDX-License-Identifier: GPL-2.0-only /* * IRQ offload/bypass manager * * Copyright (C) 2015 Red Hat, Inc. * Copyright (c) 2015 Linaro Ltd. * * Various virtualization hardware acceleration techniques allow bypassing or * offloading interrupts received from devices around the host kernel. Posted * Interrupts on Intel VT-d systems can allow interrupts to be received * directly by a virtual machine. ARM IRQ Forwarding allows forwarded physical * interrupts to be directly deactivated by the guest. This manager allows * interrupt producers and consumers to find each other to enable this sort of * bypass. */ #include <linux/irqbypass.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("IRQ bypass manager utility module"); static LIST_HEAD(producers); static LIST_HEAD(consumers); static DEFINE_MUTEX(lock); /* @lock must be held when calling connect */ static int __connect(struct irq_bypass_producer *prod, struct irq_bypass_consumer *cons) { int ret = 0; if (prod->stop) prod->stop(prod); if (cons->stop) cons->stop(cons); if (prod->add_consumer) ret = prod->add_consumer(prod, cons); if (!ret) { ret = cons->add_producer(cons, prod); if (ret && prod->del_consumer) prod->del_consumer(prod, cons); } if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); return ret; } /* @lock must be held when calling disconnect */ static void __disconnect(struct irq_bypass_producer *prod, struct irq_bypass_consumer *cons) { if (prod->stop) prod->stop(prod); if (cons->stop) cons->stop(cons); cons->del_producer(cons, prod); if (prod->del_consumer) prod->del_consumer(prod, cons); if (cons->start) cons->start(cons); if (prod->start) prod->start(prod); } /** * irq_bypass_register_producer - register IRQ bypass producer * @producer: pointer to producer structure * * Add the provided IRQ producer to the list of producers and connect * with any matching token found on the IRQ consumers list. */ int irq_bypass_register_producer(struct irq_bypass_producer *producer) { struct irq_bypass_producer *tmp; struct irq_bypass_consumer *consumer; int ret; if (!producer->token) return -EINVAL; might_sleep(); if (!try_module_get(THIS_MODULE)) return -ENODEV; mutex_lock(&lock); list_for_each_entry(tmp, &producers, node) { if (tmp->token == producer->token) { ret = -EBUSY; goto out_err; } } list_for_each_entry(consumer, &consumers, node) { if (consumer->token == producer->token) { ret = __connect(producer, consumer); if (ret) goto out_err; break; } } list_add(&producer->node, &producers); mutex_unlock(&lock); return 0; out_err: mutex_unlock(&lock); module_put(THIS_MODULE); return ret; } EXPORT_SYMBOL_GPL(irq_bypass_register_producer); /** * irq_bypass_unregister_producer - unregister IRQ bypass producer * @producer: pointer to producer structure * * Remove a previously registered IRQ producer from the list of producers * and disconnect it from any connected IRQ consumer. */ void irq_bypass_unregister_producer(struct irq_bypass_producer *producer) { struct irq_bypass_producer *tmp; struct irq_bypass_consumer *consumer; if (!producer->token) return; might_sleep(); if (!try_module_get(THIS_MODULE)) return; /* nothing in the list anyway */ mutex_lock(&lock); list_for_each_entry(tmp, &producers, node) { if (tmp->token != producer->token) continue; list_for_each_entry(consumer, &consumers, node) { if (consumer->token == producer->token) { __disconnect(producer, consumer); break; } } list_del(&producer->node); module_put(THIS_MODULE); break; } mutex_unlock(&lock); module_put(THIS_MODULE); } EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer); /** * irq_bypass_register_consumer - register IRQ bypass consumer * @consumer: pointer to consumer structure * * Add the provided IRQ consumer to the list of consumers and connect * with any matching token found on the IRQ producer list. */ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer) { struct irq_bypass_consumer *tmp; struct irq_bypass_producer *producer; int ret; if (!consumer->token || !consumer->add_producer || !consumer->del_producer) return -EINVAL; might_sleep(); if (!try_module_get(THIS_MODULE)) return -ENODEV; mutex_lock(&lock); list_for_each_entry(tmp, &consumers, node) { if (tmp->token == consumer->token || tmp == consumer) { ret = -EBUSY; goto out_err; } } list_for_each_entry(producer, &producers, node) { if (producer->token == consumer->token) { ret = __connect(producer, consumer); if (ret) goto out_err; break; } } list_add(&consumer->node, &consumers); mutex_unlock(&lock); return 0; out_err: mutex_unlock(&lock); module_put(THIS_MODULE); return ret; } EXPORT_SYMBOL_GPL(irq_bypass_register_consumer); /** * irq_bypass_unregister_consumer - unregister IRQ bypass consumer * @consumer: pointer to consumer structure * * Remove a previously registered IRQ consumer from the list of consumers * and disconnect it from any connected IRQ producer. */ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer) { struct irq_bypass_consumer *tmp; struct irq_bypass_producer *producer; if (!consumer->token) return; might_sleep(); if (!try_module_get(THIS_MODULE)) return; /* nothing in the list anyway */ mutex_lock(&lock); list_for_each_entry(tmp, &consumers, node) { if (tmp != consumer) continue; list_for_each_entry(producer, &producers, node) { if (producer->token == consumer->token) { __disconnect(producer, consumer); break; } } list_del(&consumer->node); module_put(THIS_MODULE); break; } mutex_unlock(&lock); module_put(THIS_MODULE); } EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer); |
| 255 245 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 32 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Linaro * Author: Christoffer Dall <christoffer.dall@linaro.org> */ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/interrupt.h> #include <linux/kvm_host.h> #include <linux/seq_file.h> #include <kvm/arm_vgic.h> #include <asm/kvm_mmu.h> #include "vgic.h" /* * Structure to control looping through the entire vgic state. We start at * zero for each field and move upwards. So, if dist_id is 0 we print the * distributor info. When dist_id is 1, we have already printed it and move * on. * * When vcpu_id < nr_cpus we print the vcpu info until vcpu_id == nr_cpus and * so on. */ struct vgic_state_iter { int nr_cpus; int nr_spis; int nr_lpis; int dist_id; int vcpu_id; unsigned long intid; int lpi_idx; }; static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) { struct vgic_dist *dist = &kvm->arch.vgic; if (iter->dist_id == 0) { iter->dist_id++; return; } /* * Let the xarray drive the iterator after the last SPI, as the iterator * has exhausted the sequentially-allocated INTID space. */ if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1) && iter->nr_lpis) { if (iter->lpi_idx < iter->nr_lpis) xa_find_after(&dist->lpi_xa, &iter->intid, VGIC_LPI_MAX_INTID, LPI_XA_MARK_DEBUG_ITER); iter->lpi_idx++; return; } iter->intid++; if (iter->intid == VGIC_NR_PRIVATE_IRQS && ++iter->vcpu_id < iter->nr_cpus) iter->intid = 0; } static int iter_mark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; int nr_lpis = 0; xa_for_each(&dist->lpi_xa, intid, irq) { if (!vgic_try_get_irq_kref(irq)) continue; xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); nr_lpis++; } return nr_lpis; } static void iter_unmark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) { xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); vgic_put_irq(kvm, irq); } } static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter, loff_t pos) { int nr_cpus = atomic_read(&kvm->online_vcpus); memset(iter, 0, sizeof(*iter)); iter->nr_cpus = nr_cpus; iter->nr_spis = kvm->arch.vgic.nr_spis; if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) iter->nr_lpis = iter_mark_lpis(kvm); /* Fast forward to the right position if needed */ while (pos--) iter_next(kvm, iter); } static bool end_of_vgic(struct vgic_state_iter *iter) { return iter->dist_id > 0 && iter->vcpu_id == iter->nr_cpus && iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && (!iter->nr_lpis || iter->lpi_idx > iter->nr_lpis); } static void *vgic_debug_start(struct seq_file *s, loff_t *pos) { struct kvm *kvm = s->private; struct vgic_state_iter *iter; mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; if (iter) { iter = ERR_PTR(-EBUSY); goto out; } iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { iter = ERR_PTR(-ENOMEM); goto out; } iter_init(kvm, iter, *pos); kvm->arch.vgic.iter = iter; if (end_of_vgic(iter)) iter = NULL; out: mutex_unlock(&kvm->arch.config_lock); return iter; } static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) { struct kvm *kvm = s->private; struct vgic_state_iter *iter = kvm->arch.vgic.iter; ++*pos; iter_next(kvm, iter); if (end_of_vgic(iter)) iter = NULL; return iter; } static void vgic_debug_stop(struct seq_file *s, void *v) { struct kvm *kvm = s->private; struct vgic_state_iter *iter; /* * If the seq file wasn't properly opened, there's nothing to clearn * up. */ if (IS_ERR(v)) return; mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; iter_unmark_lpis(kvm); kfree(iter); kvm->arch.vgic.iter = NULL; mutex_unlock(&kvm->arch.config_lock); } static void print_dist_state(struct seq_file *s, struct vgic_dist *dist, struct vgic_state_iter *iter) { bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3; seq_printf(s, "Distributor\n"); seq_printf(s, "===========\n"); seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2"); seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis); if (v3) seq_printf(s, "nr_lpis:\t%d\n", iter->nr_lpis); seq_printf(s, "enabled:\t%d\n", dist->enabled); seq_printf(s, "\n"); seq_printf(s, "P=pending_latch, L=line_level, A=active\n"); seq_printf(s, "E=enabled, H=hw, C=config (level=1, edge=0)\n"); seq_printf(s, "G=group\n"); } static void print_header(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int id = 0; char *hdr = "SPI "; if (vcpu) { hdr = "VCPU"; id = vcpu->vcpu_idx; } seq_printf(s, "\n"); seq_printf(s, "%s%2d TYP ID TGT_ID PLAEHCG HWID TARGET SRC PRI VCPU_ID\n", hdr, id); seq_printf(s, "----------------------------------------------------------------\n"); } static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { char *type; bool pending; if (irq->intid < VGIC_NR_SGIS) type = "SGI"; else if (irq->intid < VGIC_NR_PRIVATE_IRQS) type = "PPI"; else if (irq->intid < VGIC_MAX_SPI) type = "SPI"; else type = "LPI"; if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) print_header(s, irq, vcpu); pending = irq->pending_latch; if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; err = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &pending); WARN_ON_ONCE(err); } seq_printf(s, " %s %4d " " %2d " "%d%d%d%d%d%d%d " "%8d " "%8x " " %2x " "%3d " " %2d " "\n", type, irq->intid, (irq->target_vcpu) ? irq->target_vcpu->vcpu_idx : -1, pending, irq->line_level, irq->active, irq->enabled, irq->hw, irq->config == VGIC_CONFIG_LEVEL, irq->group, irq->hwintid, irq->mpidr, irq->source, irq->priority, (irq->vcpu) ? irq->vcpu->vcpu_idx : -1); } static int vgic_debug_show(struct seq_file *s, void *v) { struct kvm *kvm = s->private; struct vgic_state_iter *iter = v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; unsigned long flags; if (iter->dist_id == 0) { print_dist_state(s, &kvm->arch.vgic, iter); return 0; } if (!kvm->arch.vgic.initialized) return 0; if (iter->vcpu_id < iter->nr_cpus) vcpu = kvm_get_vcpu(kvm, iter->vcpu_id); /* * Expect this to succeed, as iter_mark_lpis() takes a reference on * every LPI to be visited. */ if (iter->intid < VGIC_NR_PRIVATE_IRQS) irq = vgic_get_vcpu_irq(vcpu, iter->intid); else irq = vgic_get_irq(kvm, iter->intid); if (WARN_ON_ONCE(!irq)) return -EINVAL; raw_spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; } static const struct seq_operations vgic_debug_sops = { .start = vgic_debug_start, .next = vgic_debug_next, .stop = vgic_debug_stop, .show = vgic_debug_show }; DEFINE_SEQ_ATTRIBUTE(vgic_debug); void vgic_debug_init(struct kvm *kvm) { debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm, &vgic_debug_fops); } void vgic_debug_destroy(struct kvm *kvm) { } |
| 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ #include <linux/list.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/selftests.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> #include <linux/if_hsr.h> #include <net/dcbnl.h> #include <linux/netpoll.h> #include <linux/string.h> #include "conduit.h" #include "dsa.h" #include "netlink.h" #include "port.h" #include "switch.h" #include "tag.h" #include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; struct net_device *orig_dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and * SWITCHDEV_FDB_DEL_TO_DEVICE */ unsigned char addr[ETH_ALEN]; u16 vid; bool host_addr; }; enum dsa_standalone_event { DSA_UC_ADD, DSA_UC_DEL, DSA_MC_ADD, DSA_MC_DEL, }; struct dsa_standalone_event_work { struct work_struct work; struct net_device *dev; enum dsa_standalone_event event; unsigned char addr[ETH_ALEN]; u16 vid; }; struct dsa_host_vlan_rx_filtering_ctx { struct net_device *dev; const unsigned char *addr; enum dsa_standalone_event event; }; static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) { return ds->ops->port_mdb_add && ds->ops->port_mdb_del && ds->fdb_isolation && !ds->vlan_filtering_is_global && !ds->needs_standalone_vlan_filtering; } static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; int err; switch (standalone_work->event) { case DSA_UC_ADD: err = dsa_port_standalone_host_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_UC_DEL: err = dsa_port_standalone_host_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; case DSA_MC_ADD: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_add(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to mdb: %d\n", dp->index, addr, vid, err); break; } break; case DSA_MC_DEL: ether_addr_copy(mdb.addr, addr); mdb.vid = vid; err = dsa_port_standalone_host_mdb_del(dp, &mdb); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from mdb: %d\n", dp->index, addr, vid, err); } break; } kfree(standalone_work); } static int dsa_user_schedule_standalone_work(struct net_device *dev, enum dsa_standalone_event event, const unsigned char *addr, u16 vid) { struct dsa_standalone_event_work *standalone_work; standalone_work = kzalloc(sizeof(*standalone_work), GFP_ATOMIC); if (!standalone_work) return -ENOMEM; INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; ether_addr_copy(standalone_work->addr, addr); standalone_work->vid = vid; dsa_schedule_work(&standalone_work->work); return 0; } static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } static int dsa_user_vlan_for_each(struct net_device *dev, int (*cb)(void *arg, int vid), void *arg) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; lockdep_assert_held(&dev->addr_list_lock); err = cb(arg, 0); if (err) return err; list_for_each_entry(v, &dp->user_vlans, list) { err = cb(arg, v->vid); if (err) return err; } return 0; } static int dsa_user_sync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_sync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } static int dsa_user_unsync_mc(struct net_device *dev, const unsigned char *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } void dsa_user_sync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } void dsa_user_unsync_ha(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); if (dsa_switch_supports_uc_filtering(ds) || dsa_switch_supports_mc_filtering(ds)) dsa_flush_workqueue(); } /* user mii_bus handling ***************************************************/ static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_read(ds, addr, reg); return 0xffff; } static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; if (ds->phys_mii_mask & (1 << addr)) return ds->ops->phy_write(ds, addr, reg, val); return 0; } void dsa_user_mii_bus_init(struct dsa_switch *ds) { ds->user_mii_bus->priv = (void *)ds; ds->user_mii_bus->name = "dsa user smi"; ds->user_mii_bus->read = dsa_user_phy_read; ds->user_mii_bus->write = dsa_user_phy_write; snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); ds->user_mii_bus->parent = ds->dev; ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; if (dsa_switch_supports_uc_filtering(ds)) { err = dsa_port_standalone_host_fdb_add(dp, addr, 0); if (err) goto out; } if (!ether_addr_equal(addr, conduit->dev_addr)) { err = dev_uc_add(conduit, addr); if (err < 0) goto del_host_addr; } return 0; del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, addr, 0); out: return err; } void dsa_user_host_uc_uninstall(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); } static int dsa_user_open(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); int err; err = dev_open(conduit, NULL); if (err < 0) { netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } err = dsa_user_host_uc_install(dev, dev->dev_addr); if (err) goto out; err = dsa_port_enable_rt(dp, dev->phydev); if (err) goto out_del_host_uc; return 0; out_del_host_uc: dsa_user_host_uc_uninstall(dev); out: return err; } static int dsa_user_close(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); dsa_port_disable_rt(dp); dsa_user_host_uc_uninstall(dev); return 0; } static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } static void dsa_user_change_rx_flags(struct net_device *dev, int change) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) dsa_user_manage_host_flood(dev); } static void dsa_user_set_rx_mode(struct net_device *dev) { __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } static int dsa_user_set_mac_address(struct net_device *dev, void *a) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; if (ds->ops->port_set_mac_address) { err = ds->ops->port_set_mac_address(ds, dp->index, addr->sa_data); if (err) return err; } /* If the port is down, the address isn't synced yet to hardware or * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; err = dsa_user_host_uc_install(dev, addr->sa_data); if (err) return err; dsa_user_host_uc_uninstall(dev); out_change_dev_addr: eth_hw_addr_set(dev, addr->sa_data); return 0; } struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; static int dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data) { struct dsa_user_dump_ctx *dump = data; struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; struct ndmsg *ndm; if (dump->idx < ctx->fdb_idx) goto skip; nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, sizeof(*ndm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dump->dev->ifindex; ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); skip: dump->idx++; return 0; nla_put_failure: nlmsg_cancel(dump->skb, nlh); return -EMSGSIZE; } static int dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, .idx = *idx, }; int err; err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; /* Pass through to switch driver if it supports timestamping */ switch (cmd) { case SIOCGHWTSTAMP: if (ds->ops->port_hwtstamp_get) return ds->ops->port_hwtstamp_get(ds, port, ifr); break; case SIOCSHWTSTAMP: if (ds->ops->port_hwtstamp_set) return ds->ops->port_hwtstamp_set(ds, port, ifr); break; } return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) return 0; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_PORT_MST_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_set_mst_state(dp, &attr->u.mst_state, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_BRIDGE_MST: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_mst_enable(dp, attr->u.mst, extack); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_VLAN_MSTI: if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_msti(dp, &attr->u.vlan_msti); break; default: ret = -EOPNOTSUPP; break; } return ret; } /* Must be called under rcu_read_lock() */ static int dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) continue; vid = vlan_dev_vlan_id(upper_dev); if (vid == vlan->vid) return -EBUSY; } return 0; } static int dsa_user_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, "Port already has a VLAN upper with this VID"); return err; } } return dsa_port_vlan_add(dp, vlan, extack); } /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ static int dsa_user_host_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) { NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); /* Even though drivers often handle CPU membership in special ways, * it doesn't make sense to program a PVID, so clear this flag. */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; return dsa_port_host_vlan_add(dp, &vlan, extack); } static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_add(dev, obj, extack); else err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static int dsa_user_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_vlan_del(dp, vlan); } static int dsa_user_host_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ if (!dp->bridge) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) return 0; vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); return dsa_port_host_vlan_del(dp, vlan); } static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) return 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_bridge_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) err = dsa_user_vlan_del(dev, obj); else err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del_ring_role(dp, SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; break; } return err; } static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) return; if (!ds->ops->port_txtstamp) return; ds->ops->port_txtstamp(ds, p->dp->index, skb); } netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) { /* SKB for netpoll still need to be mangled with the protocol-specific * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); memset(skb->cb, 0, sizeof(skb->cb)); /* Handle tx timestamp if any */ dsa_skb_tx_timestamp(p, skb); if (skb_ensure_writable_head_tail(skb, dev)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* needed_tailroom should still be 'warm' in the cache line from * skb_ensure_writable_head_tail(), which has also ensured that * padding is safe. */ if (dev->needed_tailroom) eth_skb_pad(skb); /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ nskb = p->xmit(skb, dev); if (!nskb) { kfree_skb(skb); return NETDEV_TX_OK; } return dsa_enqueue_skb(nskb, dev); } /* ethtool operations *******************************************************/ static void dsa_user_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_user_get_regs_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) return ds->ops->get_regs_len(ds, dp->index); return -EOPNOTSUPP; } static void dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } static int dsa_user_nway_reset(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } static int dsa_user_get_eeprom_len(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; if (ds->ops->get_eeprom_len) return ds->ops->get_eeprom_len(ds); return 0; } static int dsa_user_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) return ds->ops->get_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static int dsa_user_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) return ds->ops->set_eeprom(ds, eeprom, data); return -EOPNOTSUPP; } static void dsa_user_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { ethtool_puts(&data, "tx_packets"); ethtool_puts(&data, "tx_bytes"); ethtool_puts(&data, "rx_packets"); ethtool_puts(&data, "rx_bytes"); if (ds->ops->get_strings) ds->ops->get_strings(ds, dp->index, stringset, data); } else if (stringset == ETH_SS_TEST) { net_selftest_get_strings(data); } } static void dsa_user_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; int i; for_each_possible_cpu(i) { u64 tx_packets, tx_bytes, rx_packets, rx_bytes; s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin(&s->syncp); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); } while (u64_stats_fetch_retry(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; data[2] += rx_packets; data[3] += rx_bytes; } if (ds->ops->get_ethtool_stats) ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } static int dsa_user_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { int count = 0; if (ds->ops->get_sset_count) { count = ds->ops->get_sset_count(ds, dp->index, sset); if (count < 0) return count; } return count + 4; } else if (sset == ETH_SS_TEST) { return net_selftest_get_count(); } return -EOPNOTSUPP; } static void dsa_user_get_eth_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } static void dsa_user_get_eth_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); } static void dsa_user_get_eth_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); } static void dsa_user_get_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } static void dsa_user_get_ts_stats(struct net_device *dev, struct ethtool_ts_stats *ts_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_ts_stats) ds->ops->get_ts_stats(ds, dp->index, ts_stats); } static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { ds->ops->self_test(ds, dp->index, etest, buf); return; } net_selftest(ndev, etest, buf); } static int dsa_user_get_mm(struct net_device *dev, struct ethtool_mm_state *state) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) return -EOPNOTSUPP; return ds->ops->get_mm(ds, dp->index, state); } static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) return -EOPNOTSUPP; return ds->ops->set_mm(ds, dp->index, cfg, extack); } static void dsa_user_get_mm_stats(struct net_device *dev, struct ethtool_mm_stats *stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; phylink_ethtool_set_wol(dp->pl, w); if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); return ret; } static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; /* Check whether the switch supports EEE */ if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index)) return -EOPNOTSUPP; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev) return -ENODEV; if (!ds->ops->set_mac_eee) return -EOPNOTSUPP; ret = ds->ops->set_mac_eee(ds, dp->index, e); if (ret) return ret; return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; /* Check whether the switch supports EEE */ if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index)) return -EOPNOTSUPP; /* Port's PHY and MAC both need to be EEE capable */ if (!dev->phydev) return -ENODEV; return phylink_ethtool_get_eee(dp->pl, e); } static int dsa_user_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } static int dsa_user_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } static void dsa_user_get_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } static void dsa_user_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } static int dsa_user_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam *pause) { struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER static int dsa_user_netpoll_setup(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); if (!netpoll) return -ENOMEM; err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; } p->netpoll = netpoll; out: return err; } static void dsa_user_netpoll_cleanup(struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) return; p->netpoll = NULL; __netpoll_free(netpoll); } static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) if (mall_tc_entry->cookie == cookie) return mall_tc_entry; return NULL; } static int dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress, bool ingress_target) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; struct dsa_port *to_dp; int err; if (cls->common.protocol != htons(ETH_P_ALL)) { NL_SET_ERR_MSG_MOD(extack, "Can only offload \"protocol all\" matchall filter"); return -EOPNOTSUPP; } if (!ds->ops->port_mirror_add) { NL_SET_ERR_MSG_MOD(extack, "Switch does not support mirroring operation"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; if (!act->dev) return -EINVAL; if (dsa_user_dev_check(act->dev)) { if (ingress_target) { /* We can only fulfill this using software assist */ if (cls->common.skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Can only mirred to ingress of DSA user port if filter also runs in software"); return -EOPNOTSUPP; } to_dp = dp->cpu_dp; } else { to_dp = dsa_user_to_port(act->dev); } } else { /* Handle mirroring to foreign target ports as a mirror towards * the CPU. The software tc rule will take the packets from * there. */ if (cls->common.skip_sw) { NL_SET_ERR_MSG_MOD(extack, "Can only mirred to CPU if filter also runs in software"); return -EOPNOTSUPP; } to_dp = dp->cpu_dp; } if (dp->ds != to_dp->ds) { NL_SET_ERR_MSG_MOD(extack, "Cross-chip mirroring not implemented"); return -EOPNOTSUPP; } mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; mirror->to_local_port = to_dp->index; mirror->ingress = ingress; err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress, extack); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall_police(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; struct flow_action_entry *act; int err; if (!ds->ops->port_policer_add) { NL_SET_ERR_MSG_MOD(extack, "Policing offload not implemented"); return -EOPNOTSUPP; } if (!ingress) { NL_SET_ERR_MSG_MOD(extack, "Only supported on ingress qdisc"); return -EOPNOTSUPP; } if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { NL_SET_ERR_MSG_MOD(extack, "Only one port policer allowed"); return -EEXIST; } } act = &cls->rule->action.entries[0]; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; mall_tc_entry->cookie = cls->cookie; mall_tc_entry->type = DSA_PORT_MALL_POLICER; policer = &mall_tc_entry->policer; policer->rate_bytes_per_sec = act->police.rate_bytes_ps; policer->burst = act->police.burst; err = ds->ops->port_policer_add(ds, dp->index, policer); if (err) { kfree(mall_tc_entry); return err; } list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); return err; } static int dsa_user_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { const struct flow_action *action = &cls->rule->action; struct netlink_ext_ack *extack = cls->common.extack; if (!flow_offload_has_one_action(action)) { NL_SET_ERR_MSG_MOD(extack, "Cannot offload matchall filter with more than one action"); return -EOPNOTSUPP; } switch (action->entries[0].id) { case FLOW_ACTION_MIRRED: return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, false); case FLOW_ACTION_MIRRED_INGRESS: return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, true); case FLOW_ACTION_POLICE: return dsa_user_add_cls_matchall_police(dev, cls, ingress); default: NL_SET_ERR_MSG_MOD(extack, "Unknown action"); break; } return -EOPNOTSUPP; } static void dsa_user_del_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; list_del(&mall_tc_entry->list); switch (mall_tc_entry->type) { case DSA_PORT_MALL_MIRROR: if (ds->ops->port_mirror_del) ds->ops->port_mirror_del(ds, dp->index, &mall_tc_entry->mirror); break; case DSA_PORT_MALL_POLICER: if (ds->ops->port_policer_del) ds->ops->port_policer_del(ds, dp->index); break; default: WARN_ON(1); } kfree(mall_tc_entry); } static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_add_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_add) return -EOPNOTSUPP; return ds->ops->cls_flower_add(ds, port, cls, ingress); } static int dsa_user_del_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_del) return -EOPNOTSUPP; return ds->ops->cls_flower_del(ds, port, cls, ingress); } static int dsa_user_stats_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->cls_flower_stats) return -EOPNOTSUPP; return ds->ops->cls_flower_stats(ds, port, cls, ingress); } static int dsa_user_setup_tc_cls_flower(struct net_device *dev, struct flow_cls_offload *cls, bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; if (!tc_can_offload(dev)) return -EOPNOTSUPP; switch (type) { case TC_SETUP_CLSMATCHALL: return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, void *type_data, void *cb_priv) { return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } static LIST_HEAD(dsa_user_block_cb_list); static int dsa_user_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } } static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, void *type_data) { struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } if (!ds->ops->port_setup_tc) return -EOPNOTSUPP; return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } static int dsa_user_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) return -EOPNOTSUPP; return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } static int dsa_user_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) return -EOPNOTSUPP; return ds->ops->set_rxnfc(ds, dp->index, nfc); } static int dsa_user_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) return -EOPNOTSUPP; return ds->ops->get_ts_info(ds, p->dp->index, ts); } static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct netlink_ext_ack extack = {0}; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int ret; /* User port... */ ret = dsa_port_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); return ret; } /* And CPU port... */ ret = dsa_port_host_vlan_add(dp, &vlan, &extack); if (ret) { if (extack._msg) netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, extack._msg); return ret; } if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; v = kzalloc(sizeof(*v), GFP_KERNEL); if (!v) { ret = -ENOMEM; goto rollback; } netif_addr_lock_bh(dev); v->vid = vid; list_add_tail(&v->list, &dp->user_vlans); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; rollback: dsa_port_host_vlan_del(dp, &vlan); dsa_port_vlan_del(dp, &vlan); return ret; } static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; struct dsa_vlan *v; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; err = dsa_port_host_vlan_del(dp, &vlan); if (err) return err; if (!dsa_switch_supports_uc_filtering(ds) && !dsa_switch_supports_mc_filtering(ds)) return 0; netif_addr_lock_bh(dev); v = dsa_vlan_find(&dp->user_vlans, &vlan); if (!v) { netif_addr_unlock_bh(dev); return -ENOENT; } list_del(&v->list); kfree(v); if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, ha->addr, vid); } } netif_addr_unlock_bh(dev); dsa_flush_workqueue(); return 0; } static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_add_vid(arg, proto, vid); } static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN * filtering is enabled. The baseline is that only ports that offload a * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, * but there are exceptions for quirky hardware. * * If ds->vlan_filtering_is_global = true, then standalone ports which share * the same switch with other ports that offload a VLAN-aware bridge are also * inevitably VLAN-aware. * * To summarize, a DSA switch port offloads: * * - If standalone (this includes software bridge, software LAG): * - if ds->needs_standalone_vlan_filtering = true, OR if * (ds->vlan_filtering_is_global = true AND there are bridges spanning * this switch chip which have vlan_filtering=1) * - the 8021q upper VLANs * - else (standalone VLAN filtering is not needed, VLAN filtering is not * global, or it is, but no port is under a VLAN-aware bridge): * - no VLAN (any 8021q upper is a software VLAN) * * - If under a vlan_filtering=0 bridge which it offload: * - if ds->configure_vlan_while_not_filtering = true (default): * - the bridge VLANs. These VLANs are committed to hardware but inactive. * - else (deprecated): * - no VLAN. The bridge VLANs are not restored when VLAN awareness is * enabled, so this behavior is broken and discouraged. * * - If under a vlan_filtering=1 bridge which it offload: * - the bridge VLANs * - the 8021q upper VLANs */ int dsa_user_manage_vlan_filtering(struct net_device *user, bool vlan_filtering) { int err; if (vlan_filtering) { user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { vlan_for_each(user, dsa_user_clear_vlan, user); user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; } struct dsa_hw_port { struct list_head list; struct net_device *dev; int old_mtu; }; static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) { const struct dsa_hw_port *p; int err; list_for_each_entry(p, hw_port_list, list) { if (p->dev->mtu == mtu) continue; err = dev_set_mtu(p->dev, mtu); if (err) goto rollback; } return 0; rollback: list_for_each_entry_continue_reverse(p, hw_port_list, list) { if (p->dev->mtu == p->old_mtu) continue; if (dev_set_mtu(p->dev, p->old_mtu)) netdev_err(p->dev, "Failed to restore MTU\n"); } return err; } static void dsa_hw_port_list_free(struct list_head *hw_port_list) { struct dsa_hw_port *p, *n; list_for_each_entry_safe(p, n, hw_port_list, list) kfree(p); } /* Make the hardware datapath to/from @dev limited to a common MTU */ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) { struct list_head hw_port_list; struct dsa_switch_tree *dst; int min_mtu = ETH_MAX_MTU; struct dsa_port *other_dp; int err; if (!dp->ds->mtu_enforcement_ingress) return; if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); /* Populate the list of ports that are part of the same bridge * as the newly added/modified port */ list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; if (!dsa_port_bridge_same(dp, other_dp)) continue; if (!other_dp->ds->mtu_enforcement_ingress) continue; user = other_dp->user; if (min_mtu > user->mtu) min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; hw_port->dev = user; hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } } /* Attempt to configure the entire hardware bridge to the newly added * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; /* Clearly that didn't work out so well, so just set the minimum MTU on * all hardware bridge ports now. If this fails too, then all ports will * still have their old MTU rolled back anyway. */ dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); out: dsa_hw_port_list_free(&hw_port_list); } int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; int new_conduit_mtu; int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { int user_mtu; /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) user_mtu = new_mtu; else user_mtu = other_dp->user->mtu; if (largest_mtu < user_mtu) largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); old_conduit_mtu = conduit->mtu; new_conduit_mtu = largest_mtu + overhead; if (new_conduit_mtu > mtu_limit) return -ERANGE; /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ if (new_conduit_mtu != old_conduit_mtu) { err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. */ err = dsa_port_mtu_change(cpu_dp, cpu_mtu); if (err) goto out_cpu_failed; } err = ds->ops->port_change_mtu(ds, dp->index, new_mtu); if (err) goto out_port_failed; WRITE_ONCE(dev->mtu, new_mtu); dsa_bridge_mtu_normalization(dp); return 0; out_port_failed: if (new_conduit_mtu != old_conduit_mtu) dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: if (new_conduit_mtu != old_conduit_mtu) dev_set_mtu(conduit, old_conduit_mtu); out_conduit_failed: return err; } static int __maybe_unused dsa_user_dcbnl_set_apptrust(struct net_device *dev, u8 *sel, int nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_set_apptrust) return -EOPNOTSUPP; return ds->ops->port_set_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_get_apptrust(struct net_device *dev, u8 *sel, int *nsel) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; if (!ds->ops->port_get_apptrust) return -EOPNOTSUPP; return ds->ops->port_get_apptrust(ds, port, sel, nsel); } static int __maybe_unused dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } return 0; } /* Update the DSCP prio entries on all user ports of the switch in case * the switch supports global DSCP prio instead of per port DSCP prios. */ static int dsa_user_dcbnl_ieee_global_dscp_setdel(struct net_device *dev, struct dcb_app *app, bool del) { int (*setdel)(struct net_device *dev, struct dcb_app *app); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int err, restore_err; if (del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; err = setdel(user, app); if (err) goto err_try_to_restore; } return 0; err_try_to_restore: /* Revert logic to restore previous state of app entries */ if (!del) setdel = dcb_ieee_delapp; else setdel = dcb_ieee_setapp; dsa_switch_for_each_user_port_continue_reverse(other_dp, ds) { struct net_device *user = other_dp->user; if (!user || user == dev) continue; restore_err = setdel(user, app); if (restore_err) netdev_err(user, "Failed to restore DSCP prio entry configuration\n"); } return err; } static int __maybe_unused dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_add_dscp_prio) return -EOPNOTSUPP; if (dscp >= 64) { netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n", dscp); return -EINVAL; } err = dcb_ieee_setapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = __fls(mask); err = ds->ops->port_add_dscp_prio(ds, port, dscp, new_prio); if (err) { dcb_ieee_delapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, false); if (err) { if (ds->ops->port_del_dscp_prio) ds->ops->port_del_dscp_prio(ds, port, dscp, new_prio); dcb_ieee_delapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_set_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_add_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } static int __maybe_unused dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; if (!ds->ops->port_set_default_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; mask = dcb_ieee_getapp_mask(dev, app); new_prio = mask ? __fls(mask) : 0; err = ds->ops->port_set_default_prio(ds, port, new_prio); if (err) { dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err, port = dp->index; u8 dscp = app->protocol; if (!ds->ops->port_del_dscp_prio) return -EOPNOTSUPP; err = dcb_ieee_delapp(dev, app); if (err) return err; err = ds->ops->port_del_dscp_prio(ds, port, dscp, app->priority); if (err) { dcb_ieee_setapp(dev, app); return err; } if (!ds->dscp_prio_mapping_is_global) return 0; err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, true); if (err) { if (ds->ops->port_add_dscp_prio) ds->ops->port_add_dscp_prio(ds, port, dscp, app->priority); dcb_ieee_setapp(dev, app); return err; } return 0; } static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: return dsa_user_dcbnl_del_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: return dsa_user_dcbnl_del_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } /* Pre-populate the DCB application priority table with the priorities * configured during switch setup, which we read from hardware here. */ static int dsa_user_dcbnl_init(struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; int err; if (ds->ops->port_get_default_prio) { int prio = ds->ops->port_get_default_prio(ds, port); struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, .protocol = 0, .priority = prio, }; if (prio < 0) return prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } if (ds->ops->port_get_dscp_prio) { int protocol; for (protocol = 0; protocol < 64; protocol++) { struct dcb_app app = { .selector = IEEE_8021QAZ_APP_SEL_DSCP, .protocol = protocol, }; int prio; prio = ds->ops->port_get_dscp_prio(ds, port, protocol); if (prio == -EOPNOTSUPP) continue; if (prio < 0) return prio; app.priority = prio; err = dcb_ieee_setapp(dev, &app); if (err) return err; } } return 0; } static const struct ethtool_ops dsa_user_ethtool_ops = { .get_drvinfo = dsa_user_get_drvinfo, .get_regs_len = dsa_user_get_regs_len, .get_regs = dsa_user_get_regs, .nway_reset = dsa_user_nway_reset, .get_link = ethtool_op_get_link, .get_eeprom_len = dsa_user_get_eeprom_len, .get_eeprom = dsa_user_get_eeprom, .set_eeprom = dsa_user_set_eeprom, .get_strings = dsa_user_get_strings, .get_ethtool_stats = dsa_user_get_ethtool_stats, .get_sset_count = dsa_user_get_sset_count, .get_eth_phy_stats = dsa_user_get_eth_phy_stats, .get_eth_mac_stats = dsa_user_get_eth_mac_stats, .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, .get_rmon_stats = dsa_user_get_rmon_stats, .get_ts_stats = dsa_user_get_ts_stats, .set_wol = dsa_user_set_wol, .get_wol = dsa_user_get_wol, .set_eee = dsa_user_set_eee, .get_eee = dsa_user_get_eee, .get_link_ksettings = dsa_user_get_link_ksettings, .set_link_ksettings = dsa_user_set_link_ksettings, .get_pause_stats = dsa_user_get_pause_stats, .get_pauseparam = dsa_user_get_pauseparam, .set_pauseparam = dsa_user_set_pauseparam, .get_rxnfc = dsa_user_get_rxnfc, .set_rxnfc = dsa_user_set_rxnfc, .get_ts_info = dsa_user_get_ts_info, .self_test = dsa_user_net_selftest, .get_mm = dsa_user_get_mm, .set_mm = dsa_user_set_mm, .get_mm_stats = dsa_user_get_mm_stats, }; static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { .ieee_setapp = dsa_user_dcbnl_ieee_setapp, .ieee_delapp = dsa_user_dcbnl_ieee_delapp, .dcbnl_setapptrust = dsa_user_dcbnl_set_apptrust, .dcbnl_getapptrust = dsa_user_dcbnl_get_apptrust, }; static void dsa_user_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_stats64) ds->ops->get_stats64(ds, dp->index, s); else dev_get_tstats64(dev, s); } static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct dsa_port *dp = dsa_user_to_port(ctx->dev); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_port *cpu_dp = dp->cpu_dp; path->dev = ctx->dev; path->type = DEV_PATH_DSA; path->dsa.proto = cpu_dp->tag_ops->proto; path->dsa.port = dp->index; ctx->dev = conduit; return 0; } static const struct net_device_ops dsa_user_netdev_ops = { .ndo_open = dsa_user_open, .ndo_stop = dsa_user_close, .ndo_start_xmit = dsa_user_xmit, .ndo_change_rx_flags = dsa_user_change_rx_flags, .ndo_set_rx_mode = dsa_user_set_rx_mode, .ndo_set_mac_address = dsa_user_set_mac_address, .ndo_fdb_dump = dsa_user_fdb_dump, .ndo_eth_ioctl = dsa_user_ioctl, .ndo_get_iflink = dsa_user_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = dsa_user_netpoll_setup, .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, .ndo_poll_controller = dsa_user_poll_controller, #endif .ndo_setup_tc = dsa_user_setup_tc, .ndo_get_stats64 = dsa_user_get_stats64, .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, .ndo_change_mtu = dsa_user_change_mtu, .ndo_fill_forward_path = dsa_user_fill_forward_path, }; static const struct device_type dsa_type = { .name = "dsa", }; void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) { const struct dsa_port *dp = dsa_to_port(ds, port); if (dp->pl) phylink_mac_change(dp->pl, up); } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); static void dsa_user_phylink_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; /* No need to check that this operation is valid, the callback would * not be called if it was not. */ ds->ops->phylink_fixed_state(ds, dp->index, state); } /* user device setup *******************************************************/ static int dsa_user_phy_connect(struct net_device *user_dev, int addr, u32 flags) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_switch *ds = dp->ds; user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); if (!user_dev->phydev) { netdev_err(user_dev, "no phy at %d\n", addr); return -ENODEV; } user_dev->phydev->dev_flags |= flags; return phylink_connect_phy(dp->pl, user_dev->phydev); } static int dsa_user_phy_setup(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; u32 phy_flags = 0; int ret; dp->pl_config.dev = &user_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; /* The get_fixed_state callback takes precedence over polling the * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set * this if the switch provides such a callback. */ if (ds->ops->phylink_fixed_state) { dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; dp->pl_config.poll_fixed_state = true; } ret = dsa_port_phylink_create(dp); if (ret) return ret; if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); if (ret == -ENODEV && ds->user_mii_bus) { /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); } if (ret) { netdev_err(user_dev, "failed to connect to PHY: %pe\n", ERR_PTR(ret)); dsa_port_phylink_destroy(dp); } return ret; } void dsa_user_setup_tagger(struct net_device *user) { struct dsa_port *dp = dsa_user_to_port(user); struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_user_priv *p = netdev_priv(user); const struct dsa_port *cpu_dp = dp->cpu_dp; const struct dsa_switch *ds = dp->ds; user->needed_headroom = cpu_dp->tag_ops->needed_headroom; user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the conduit) * by also inheriting the conduit's needed headroom and tailroom. * The 8021q driver also does this. */ user->needed_headroom += conduit->needed_headroom; user->needed_tailroom += conduit->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; user->features = conduit->vlan_features | NETIF_F_HW_TC; user->hw_features |= NETIF_F_HW_TC; if (user->needed_tailroom) user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; user->lltx = true; } int dsa_user_suspend(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_detach(user_dev); rtnl_lock(); phylink_stop(dp->pl); rtnl_unlock(); return 0; } int dsa_user_resume(struct net_device *user_dev) { struct dsa_port *dp = dsa_user_to_port(user_dev); if (!netif_running(user_dev)) return 0; netif_device_attach(user_dev); rtnl_lock(); phylink_start(dp->pl); rtnl_unlock(); return 0; } int dsa_user_create(struct dsa_port *port) { struct net_device *conduit = dsa_port_to_conduit(port); struct dsa_switch *ds = port->ds; struct net_device *user_dev; struct dsa_user_priv *p; const char *name; int assign_type; int ret; if (!ds->num_tx_queues) ds->num_tx_queues = 1; if (port->name) { name = port->name; assign_type = NET_NAME_PREDICTABLE; } else { name = "eth%d"; assign_type = NET_NAME_ENUM; } user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, assign_type, ether_setup, ds->num_tx_queues, 1); if (user_dev == NULL) return -ENOMEM; user_dev->rtnl_link_ops = &dsa_link_ops; user_dev->ethtool_ops = &dsa_user_ethtool_ops; #if IS_ENABLED(CONFIG_DCB) user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; #endif if (!is_zero_ether_addr(port->mac)) eth_hw_addr_set(user_dev, port->mac); else eth_hw_addr_inherit(user_dev, conduit); user_dev->priv_flags |= IFF_NO_QUEUE; if (dsa_switch_supports_uc_filtering(ds)) user_dev->priv_flags |= IFF_UNICAST_FLT; user_dev->netdev_ops = &dsa_user_netdev_ops; if (ds->ops->port_max_mtu) user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); SET_NETDEV_DEVTYPE(user_dev, &dsa_type); SET_NETDEV_DEV(user_dev, port->ds->dev); SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); user_dev->dev.of_node = port->dn; user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) goto out_free; p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); port->user = user_dev; dsa_user_setup_tagger(user_dev); netif_carrier_off(user_dev); ret = dsa_user_phy_setup(user_dev); if (ret) { netdev_err(user_dev, "error %d setting up PHY for tree %d, switch %d, port %d\n", ret, ds->dst->index, ds->index, port->index); goto out_gcells; } rtnl_lock(); ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", ret, ETH_DATA_LEN, port->index); ret = register_netdevice(user_dev); if (ret) { netdev_err(conduit, "error %d registering interface %s\n", ret, user_dev->name); rtnl_unlock(); goto out_phy; } if (IS_ENABLED(CONFIG_DCB)) { ret = dsa_user_dcbnl_init(user_dev); if (ret) { netdev_err(user_dev, "failed to initialize DCB: %pe\n", ERR_PTR(ret)); rtnl_unlock(); goto out_unregister; } } ret = netdev_upper_dev_link(conduit, user_dev, NULL); rtnl_unlock(); if (ret) goto out_unregister; return 0; out_unregister: unregister_netdev(user_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(p->dp); out_gcells: gro_cells_destroy(&p->gcells); out_free: free_netdev(user_dev); port->user = NULL; return ret; } void dsa_user_destroy(struct net_device *user_dev) { struct net_device *conduit = dsa_user_to_conduit(user_dev); struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_user_priv *p = netdev_priv(user_dev); netif_carrier_off(user_dev); rtnl_lock(); netdev_upper_dev_unlink(conduit, user_dev); unregister_netdevice(user_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); free_netdev(user_dev); } int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack) { struct net_device *old_conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct net_device *upper; struct list_head *iter; int err; if (conduit == old_conduit) return 0; if (!ds->ops->port_change_conduit) { NL_SET_ERR_MSG_MOD(extack, "Driver does not support changing DSA conduit"); return -EOPNOTSUPP; } if (!netdev_uses_dsa(conduit)) { NL_SET_ERR_MSG_MOD(extack, "Interface not eligible as DSA conduit"); return -EOPNOTSUPP; } netdev_for_each_upper_dev_rcu(conduit, upper, iter) { if (dsa_user_dev_check(upper)) continue; if (netif_is_bridge_master(upper)) continue; NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); return -EOPNOTSUPP; } /* Since we allow live-changing the DSA conduit, plus we auto-open the * DSA conduit when the user port opens => we need to ensure that the * new DSA conduit is open too. */ if (dev->flags & IFF_UP) { err = dev_open(conduit, extack); if (err) return err; } netdev_upper_dev_unlink(old_conduit, dev); err = netdev_upper_dev_link(conduit, dev, extack); if (err) goto out_revert_old_conduit_unlink; err = dsa_port_change_conduit(dp, conduit, extack); if (err) goto out_revert_conduit_link; /* Update the MTU of the new CPU port through cross-chip notifiers */ err = dsa_user_change_mtu(dev, dev->mtu); if (err && err != -EOPNOTSUPP) { netdev_warn(dev, "nonfatal error updating MTU with new conduit: %pe\n", ERR_PTR(err)); } return 0; out_revert_conduit_link: netdev_upper_dev_unlink(conduit, dev); out_revert_old_conduit_unlink: netdev_upper_dev_link(old_conduit, dev, NULL); return err; } bool dsa_user_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_user_netdev_ops; } EXPORT_SYMBOL_GPL(dsa_user_dev_check); static int dsa_user_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return err; dp = dsa_user_to_port(dev); extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_bridge_master(info->upper_dev)) { if (info->linking) { err = dsa_port_bridge_join(dp, info->upper_dev, extack); if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_lag_leave(dp, info->upper_dev); err = NOTIFY_OK; } } else if (is_hsr_master(info->upper_dev)) { if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev, extack); if (err == -EOPNOTSUPP) { NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); err = 0; } err = notifier_from_errno(err); } else { dsa_port_hsr_leave(dp, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp; if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; dp = dsa_user_to_port(dev); if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) dsa_port_pre_lag_leave(dp, info->upper_dev); /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot * meaningfully placed under a bridge yet */ return NOTIFY_DONE; } static int dsa_user_lag_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_changeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } /* Same as dsa_user_lag_changeupper() except that it calls * dsa_user_prechangeupper() */ static int dsa_user_lag_prechangeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; int err = NOTIFY_DONE; struct dsa_port *dp; if (!netif_is_lag_master(dev)) return err; netdev_for_each_lower_dev(dev, lower, iter) { if (!dsa_user_dev_check(lower)) continue; dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; err = dsa_user_prechangeupper(lower, info); if (notifier_to_errno(err)) break; } return err; } static int dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; struct net_device *user, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); if (!is_vlan_dev(dev)) return NOTIFY_DONE; user = vlan_dev_real_dev(dev); if (!dsa_user_dev_check(user)) return NOTIFY_DONE; dp = dsa_user_to_port(user); br = dsa_port_bridge_dev_get(dp); if (!br) return NOTIFY_DONE; /* Deny enslaving a VLAN device into a VLAN-aware bridge */ if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, "Cannot make VLAN device join VLAN-aware bridge"); return notifier_from_errno(-EINVAL); } return NOTIFY_DONE; } static int dsa_user_check_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; int err = NOTIFY_DONE; u16 vid; if (!br || !br_vlan_enabled(br)) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); vid = vlan_dev_vlan_id(info->upper_dev); /* br_vlan_get_info() returns -EINVAL or -ENOENT if the * device, respectively the VID is not found, returning * 0 means success, which is a failure for us here. */ err = br_vlan_get_info(br, vid, &br_info); if (err == 0) { NL_SET_ERR_MSG_MOD(extack, "This VLAN is already configured by the bridge"); return notifier_from_errno(-EBUSY); } return NOTIFY_DONE; } static int dsa_user_prechangeupper_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_switch *ds; struct dsa_port *dp; int err; if (!dsa_user_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, info); dp = dsa_user_to_port(dev); ds = dp->ds; if (ds->ops->port_prechangeupper) { err = ds->ops->port_prechangeupper(ds, dp->index, info); if (err) return notifier_from_errno(err); } if (is_vlan_dev(info->upper_dev)) return dsa_user_check_8021q_upper(dev, info); return NOTIFY_DONE; } /* To be eligible as a DSA conduit, a LAG must have all lower interfaces be * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of * switches in the same switch tree. */ static int dsa_lag_conduit_validate(struct net_device *lag_dev, struct netlink_ext_ack *extack) { struct net_device *lower1, *lower2; struct list_head *iter1, *iter2; netdev_for_each_lower_dev(lag_dev, lower1, iter1) { netdev_for_each_lower_dev(lag_dev, lower2, iter2) { if (!netdev_uses_dsa(lower1) || !netdev_uses_dsa(lower2)) { NL_SET_ERR_MSG_MOD(extack, "All LAG ports must be eligible as DSA conduits"); return notifier_from_errno(-EINVAL); } if (lower1 == lower2) continue; if (!dsa_port_tree_same(lower1->dsa_ptr, lower2->dsa_ptr)) { NL_SET_ERR_MSG_MOD(extack, "LAG contains DSA conduits of disjoint switch trees"); return notifier_from_errno(-EINVAL); } } } return NOTIFY_DONE; } static int dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); if (!netdev_uses_dsa(conduit)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; /* Allow DSA switch uppers */ if (dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; /* Allow bridge uppers of DSA conduits, subject to further * restrictions in dsa_bridge_prechangelower_sanity_check() */ if (netif_is_bridge_master(info->upper_dev)) return NOTIFY_DONE; /* Allow LAG uppers, subject to further restrictions in * dsa_lag_conduit_prechangelower_sanity_check() */ if (netif_is_lag_master(info->upper_dev)) return dsa_lag_conduit_validate(info->upper_dev, extack); NL_SET_ERR_MSG_MOD(extack, "DSA conduit cannot join unknown upper interfaces"); return notifier_from_errno(-EBUSY); } static int dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); struct net_device *lag_dev = info->upper_dev; struct net_device *lower; struct list_head *iter; if (!netdev_uses_dsa(lag_dev) || !netif_is_lag_master(lag_dev)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; if (!netdev_uses_dsa(dev)) { NL_SET_ERR_MSG(extack, "Only DSA conduits can join a LAG DSA conduit"); return notifier_from_errno(-EINVAL); } netdev_for_each_lower_dev(lag_dev, lower, iter) { if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { NL_SET_ERR_MSG(extack, "Interface is DSA conduit for a different switch tree than this LAG"); return notifier_from_errno(-EINVAL); } break; } return NOTIFY_DONE; } /* Don't allow bridging of DSA conduits, since the bridge layer rx_handler * prevents the DSA fake ethertype handler to be invoked, so we don't get the * chance to strip off and parse the DSA switch tag protocol header (the bridge * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these * frames). * The only case where that would not be an issue is when bridging can already * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev * port, and is bridged only with other ports from the same hardware device. */ static int dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, struct netdev_notifier_changeupper_info *info) { struct net_device *br = info->upper_dev; struct netlink_ext_ack *extack; struct net_device *lower; struct list_head *iter; if (!netif_is_bridge_master(br)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; extack = netdev_notifier_info_to_extack(&info->info); netdev_for_each_lower_dev(br, lower, iter) { if (!netdev_uses_dsa(new_lower) && !netdev_uses_dsa(lower)) continue; if (!netdev_port_same_parent_id(lower, new_lower)) { NL_SET_ERR_MSG(extack, "Cannot do software bridging with a DSA conduit"); return notifier_from_errno(-EINVAL); } } return NOTIFY_DONE; } static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, struct net_device *lag_dev) { struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); struct dsa_port *dp; int err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, new_conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", new_conduit->name, ERR_PTR(err)); } } } static int dsa_conduit_lag_join(struct net_device *conduit, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack) { struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; int err; err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); if (err) return err; dsa_tree_for_each_user_port(dp, dst) { if (dsa_port_to_conduit(dp) != conduit) continue; err = dsa_user_change_conduit(dp->user, lag_dev, extack); if (err) goto restore; } return 0; restore: dsa_tree_for_each_user_port_continue_reverse(dp, dst) { if (dsa_port_to_conduit(dp) != lag_dev) continue; err = dsa_user_change_conduit(dp->user, conduit, NULL); if (err) { netdev_err(dp->user, "failed to restore conduit to %s: %pe\n", conduit->name, ERR_PTR(err)); } } dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); return err; } static void dsa_conduit_lag_leave(struct net_device *conduit, struct net_device *lag_dev) { struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *new_cpu_dp = NULL; struct net_device *lower; struct list_head *iter; netdev_for_each_lower_dev(lag_dev, lower, iter) { if (netdev_uses_dsa(lower)) { new_cpu_dp = lower->dsa_ptr; break; } } if (new_cpu_dp) { /* Update the CPU port of the user ports still under the LAG * so that dsa_port_to_conduit() continues to work properly */ dsa_tree_for_each_user_port(dp, dst) if (dsa_port_to_conduit(dp) == lag_dev) dp->cpu_dp = new_cpu_dp; /* Update the index of the virtual CPU port to match the lowest * physical CPU port */ lag_dev->dsa_ptr = new_cpu_dp; wmb(); } else { /* If the LAG DSA conduit has no ports left, migrate back all * user ports to the first physical CPU port */ dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); } /* This DSA conduit has left its LAG in any case, so let * the CPU port leave the hardware LAG as well */ dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); } static int dsa_conduit_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; if (!netdev_uses_dsa(dev)) return err; extack = netdev_notifier_info_to_extack(&info->info); if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { err = dsa_conduit_lag_join(dev, info->upper_dev, info->upper_info, extack); err = notifier_from_errno(err); } else { dsa_conduit_lag_leave(dev, info->upper_dev); err = NOTIFY_OK; } } return err; } static int dsa_user_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; int err; err = dsa_user_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_conduit_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_bridge_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; err = dsa_user_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGEUPPER: { int err; err = dsa_user_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_user_lag_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; err = dsa_conduit_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; break; } case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; int err = 0; if (dsa_user_dev_check(dev)) { dp = dsa_user_to_port(dev); err = dsa_port_lag_change(dp, info->lower_state_info); } /* Mirror LAG port events on DSA conduits that are in * a LAG towards their respective switch CPU ports */ if (netdev_uses_dsa(dev)) { dp = dev->dsa_ptr; err = dsa_port_lag_change(dp, info->lower_state_info); } return notifier_from_errno(err); } case NETDEV_CHANGE: case NETDEV_UP: { /* Track state of conduit port. * DSA driver may require the conduit port (and indirectly * the tagger) to be available for some special operation. */ if (netdev_uses_dsa(dev)) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->ds->dst; /* Track when the conduit port is UP */ dsa_tree_conduit_oper_state_change(dst, dev, netif_oper_up(dev)); /* Track when the conduit port is ready and can accept * packet. * NETDEV_UP event is not enough to flag a port as ready. * We also have to wait for linkwatch_do_dev to dev_activate * and emit a NETDEV_CHANGE event. * We check if a conduit port is ready by checking if the dev * have a qdisc assigned and is not noop. */ dsa_tree_conduit_admin_state_change(dst, dev, !qdisc_tx_is_noop(dev)); return NOTIFY_OK; } return NOTIFY_DONE; } case NETDEV_GOING_DOWN: { struct dsa_port *dp, *cpu_dp; struct dsa_switch_tree *dst; LIST_HEAD(close_list); if (!netdev_uses_dsa(dev)) return NOTIFY_DONE; cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; dsa_tree_conduit_admin_state_change(dst, dev, false); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) continue; if (dp->cpu_dp != cpu_dp) continue; list_add(&dp->user->close_list, &close_list); } dev_close_many(&close_list, true); return NOTIFY_OK; } default: break; } return NOTIFY_DONE; } static void dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) { struct switchdev_notifier_fdb_info info = {}; info.addr = switchdev_work->addr; info.vid = switchdev_work->vid; info.offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, switchdev_work->orig_dev, &info.info, NULL); } static void dsa_user_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); const unsigned char *addr = switchdev_work->addr; struct net_device *dev = switchdev_work->dev; u16 vid = switchdev_work->vid; struct dsa_switch *ds; struct dsa_port *dp; int err; dp = dsa_user_to_port(dev); ds = dp->ds; switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_add(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_add(dp, addr, vid); else err = dsa_port_fdb_add(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", dp->index, addr, vid, err); break; } dsa_fdb_offload_notify(switchdev_work); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: if (switchdev_work->host_addr) err = dsa_port_bridge_host_fdb_del(dp, addr, vid); else if (dp->lag) err = dsa_port_lag_fdb_del(dp, addr, vid); else err = dsa_port_fdb_del(dp, addr, vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", dp->index, addr, vid, err); } break; } kfree(switchdev_work); } static bool dsa_foreign_dev_check(const struct net_device *dev, const struct net_device *foreign_dev) { const struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) return !dsa_tree_offloads_bridge_dev(dst, foreign_dev); if (netif_is_bridge_port(foreign_dev)) return !dsa_tree_offloads_bridge_port(dst, foreign_dev); /* Everything else is foreign */ return true; } static int dsa_user_fdb_event(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, const struct switchdev_notifier_fdb_info *fdb_info) { struct dsa_switchdev_event_work *switchdev_work; struct dsa_port *dp = dsa_user_to_port(dev); bool host_addr = fdb_info->is_local; struct dsa_switch *ds = dp->ds; if (ctx && ctx != dp) return 0; if (!dp->bridge) return 0; if (switchdev_fdb_is_dynamically_learned(fdb_info)) { if (dsa_port_offloads_bridge_port(dp, orig_dev)) return 0; /* FDB entries learned by the software bridge or by foreign * bridge ports should be installed as host addresses only if * the driver requests assisted learning. */ if (!ds->assisted_learning_on_cpu_port) return 0; } /* Also treat FDB entries on foreign interfaces bridged with us as host * addresses. */ if (dsa_foreign_dev_check(dev, orig_dev)) host_addr = true; /* Check early that we're not doing work in vain. * Host addresses on LAG ports still require regular FDB ops, * since the CPU port isn't in a LAG. */ if (dp->lag && !host_addr) { if (!ds->ops->lag_fdb_add || !ds->ops->lag_fdb_del) return -EOPNOTSUPP; } else { if (!ds->ops->port_fdb_add || !ds->ops->port_fdb_del) return -EOPNOTSUPP; } switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); if (!switchdev_work) return -ENOMEM; netdev_dbg(dev, "%s FDB entry towards %s, addr %pM vid %d%s\n", event == SWITCHDEV_FDB_ADD_TO_DEVICE ? "Adding" : "Deleting", orig_dev->name, fdb_info->addr, fdb_info->vid, host_addr ? " as host address" : ""); INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); switchdev_work->event = event; switchdev_work->dev = dev; switchdev_work->orig_dev = orig_dev; ether_addr_copy(switchdev_work->addr, fdb_info->addr); switchdev_work->vid = fdb_info->vid; switchdev_work->host_addr = host_addr; dsa_schedule_work(&switchdev_work->work); return 0; } /* Called under rcu_read_lock() */ static int dsa_user_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: err = switchdev_handle_fdb_event_to_device(dev, event, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_fdb_event); return notifier_from_errno(err); default: return NOTIFY_DONE; } return NOTIFY_OK; } static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; switch (event) { case SWITCHDEV_PORT_OBJ_ADD: err = switchdev_handle_port_obj_add_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: err = switchdev_handle_port_obj_del_foreign(dev, ptr, dsa_user_dev_check, dsa_foreign_dev_check, dsa_user_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_user_dev_check, dsa_user_port_attr_set); return notifier_from_errno(err); } return NOTIFY_DONE; } static struct notifier_block dsa_user_nb __read_mostly = { .notifier_call = dsa_user_netdevice_event, }; struct notifier_block dsa_user_switchdev_notifier = { .notifier_call = dsa_user_switchdev_event, }; struct notifier_block dsa_user_switchdev_blocking_notifier = { .notifier_call = dsa_user_switchdev_blocking_event, }; int dsa_user_register_notifier(void) { struct notifier_block *nb; int err; err = register_netdevice_notifier(&dsa_user_nb); if (err) return err; err = register_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) goto err_switchdev_nb; nb = &dsa_user_switchdev_blocking_notifier; err = register_switchdev_blocking_notifier(nb); if (err) goto err_switchdev_blocking_nb; return 0; err_switchdev_blocking_nb: unregister_switchdev_notifier(&dsa_user_switchdev_notifier); err_switchdev_nb: unregister_netdevice_notifier(&dsa_user_nb); return err; } void dsa_user_unregister_notifier(void) { struct notifier_block *nb; int err; nb = &dsa_user_switchdev_blocking_notifier; err = unregister_switchdev_blocking_notifier(nb); if (err) pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); err = unregister_netdevice_notifier(&dsa_user_nb); if (err) pr_err("DSA: failed to unregister user notifier (%d)\n", err); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_CHECKSUM_H #define __ASM_CHECKSUM_H #include <linux/in6.h> #define _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, __wsum sum); static inline __sum16 csum_fold(__wsum csum) { u32 sum = (__force u32)csum; sum += (sum >> 16) | (sum << 16); return ~(__force __sum16)(sum >> 16); } #define csum_fold csum_fold static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force __wsum)(sum >> 32)); } #define ip_fast_csum ip_fast_csum extern unsigned int do_csum(const unsigned char *buff, int len); #define do_csum do_csum #include <asm-generic/checksum.h> #endif /* __ASM_CHECKSUM_H */ |
| 581 208 524 1008 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_ATOMIC_H_ #include <linux/atomic.h> #include <linux/compiler.h> #include <asm/barrier.h> /* * Implementation of atomic bitops using atomic-fetch ops. * See Documentation/atomic_bitops.txt for details. */ static __always_inline void arch_set_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline void arch_clear_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline void arch_change_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); } static __always_inline int arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); old = raw_atomic_long_fetch_or(mask, (atomic_long_t *)p); return !!(old & mask); } static __always_inline int arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); old = raw_atomic_long_fetch_andnot(mask, (atomic_long_t *)p); return !!(old & mask); } static __always_inline int arch_test_and_change_bit(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); old = raw_atomic_long_fetch_xor(mask, (atomic_long_t *)p); return !!(old & mask); } #include <asm-generic/bitops/instrumented-atomic.h> #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */ |
| 527 529 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/init.c * * Copyright (C) 1995-2005 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/errno.h> #include <linux/swap.h> #include <linux/init.h> #include <linux/cache.h> #include <linux/mman.h> #include <linux/nodemask.h> #include <linux/initrd.h> #include <linux/gfp.h> #include <linux/math.h> #include <linux/memblock.h> #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> #include <linux/efi.h> #include <linux/swiotlb.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/hugetlb.h> #include <linux/acpi_iort.h> #include <linux/kmemleak.h> #include <linux/execmem.h> #include <asm/boot.h> #include <asm/fixmap.h> #include <asm/kasan.h> #include <asm/kernel-pgtable.h> #include <asm/kvm_host.h> #include <asm/memory.h> #include <asm/numa.h> #include <asm/rsi.h> #include <asm/sections.h> #include <asm/setup.h> #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/alternative.h> #include <asm/xen/swiotlb-xen.h> /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() * executes, which assigns it its actual value. So use a default value * that cannot be mistaken for a real physical address. */ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* * If the corresponding config options are enabled, we create both ZONE_DMA * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, * otherwise it is empty. */ phys_addr_t __ro_after_init arm64_dma_phys_limit; /* * To make optimal use of block mappings when laying out the linear * mapping, round down the base of physical memory to a size that can * be mapped efficiently, i.e., either PUD_SIZE (4k granule) or PMD_SIZE * (64k granule), or a multiple that can be mapped using contiguous bits * in the page tables: 32 * PMD_SIZE (16k granule) */ #if defined(CONFIG_ARM64_4K_PAGES) #define ARM64_MEMSTART_SHIFT PUD_SHIFT #elif defined(CONFIG_ARM64_16K_PAGES) #define ARM64_MEMSTART_SHIFT CONT_PMD_SHIFT #else #define ARM64_MEMSTART_SHIFT PMD_SHIFT #endif /* * sparsemem vmemmap imposes an additional requirement on the alignment of * memstart_addr, due to the fact that the base of the vmemmap region * has a direct correspondence, and needs to appear sufficiently aligned * in the virtual address space. */ #if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS #define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) #else #define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) #endif static void __init arch_reserve_crashkernel(void) { unsigned long long low_size = 0; unsigned long long crash_base, crash_size; char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), &crash_size, &crash_base, &low_size, &high); if (ret) return; reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high); } static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit) { return min(zone_limit, memblock_end_of_DRAM() - 1) + 1; } static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; phys_addr_t __maybe_unused acpi_zone_dma_limit; phys_addr_t __maybe_unused dt_zone_dma_limit; phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(DMA_BIT_MASK(32)); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address(); dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL); zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit); /* * Information we get from firmware (e.g. DT dma-ranges) describe DMA * bus constraints. Devices using DMA might have their own limitations. * Some of them rely on DMA zone in low 32-bit memory. Keep low RAM * DMA zone on platforms that have RAM there. */ if (memblock_start_of_DRAM() < U32_MAX) zone_dma_limit = min(zone_dma_limit, U32_MAX); arm64_dma_phys_limit = max_zone_phys(zone_dma_limit); max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); if (!arm64_dma_phys_limit) arm64_dma_phys_limit = dma32_phys_limit; #endif if (!arm64_dma_phys_limit) arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max_pfn; free_area_init(max_zone_pfns); } int pfn_is_map_memory(unsigned long pfn) { phys_addr_t addr = PFN_PHYS(pfn); /* avoid false positives for bogus PFNs, see comment in pfn_valid() */ if (PHYS_PFN(addr) != pfn) return 0; return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_is_map_memory); static phys_addr_t memory_limit __ro_after_init = PHYS_ADDR_MAX; /* * Limit the memory size that was specified via FDT. */ static int __init early_mem(char *p) { if (!p) return 1; memory_limit = memparse(p, &p) & PAGE_MASK; pr_notice("Memory limited to %lldMB\n", memory_limit >> 20); return 0; } early_param("mem", early_mem); void __init arm64_memblock_init(void) { s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual); /* * Corner case: 52-bit VA capable systems running KVM in nVHE mode may * be limited in their ability to support a linear map that exceeds 51 * bits of VA space, depending on the placement of the ID map. Given * that the placement of the ID map may be randomized, let's simply * limit the kernel's linear map to 51 bits as well if we detect this * configuration. */ if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 && is_hyp_mode_available() && !is_kernel_in_hyp_mode()) { pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n"); linear_region_size = min_t(u64, linear_region_size, BIT(51)); } /* Remove memory above our supported physical address size */ memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX); /* * Select a suitable value for the base of physical memory. */ memstart_addr = round_down(memblock_start_of_DRAM(), ARM64_MEMSTART_ALIGN); if ((memblock_end_of_DRAM() - memstart_addr) > linear_region_size) pr_warn("Memory doesn't fit in the linear mapping, VA_BITS too small\n"); /* * Remove the memory that we will not be able to cover with the * linear mapping. Take care not to clip the kernel which may be * high in memory. */ memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa_symbol(_end)), ULLONG_MAX); if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) { /* ensure that memstart_addr remains sufficiently aligned */ memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size, ARM64_MEMSTART_ALIGN); memblock_remove(0, memstart_addr); } /* * If we are running with a 52-bit kernel VA config on a system that * does not support it, we have to place the available physical * memory in the 48-bit addressable part of the linear region, i.e., * we have to move it upward. Since memstart_addr represents the * physical address of PAGE_OFFSET, we have to *subtract* from it. */ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52); /* * Apply the memory limit if it was set. Since the kernel may be loaded * high up in memory, add back the kernel region that must be accessible * via the linear mapping. */ if (memory_limit != PHYS_ADDR_MAX) { memblock_mem_limit_remove_map(memory_limit); memblock_add(__pa_symbol(_text), (u64)(_end - _text)); } if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* * Add back the memory we just removed if it results in the * initrd to become inaccessible via the linear mapping. * Otherwise, this is a no-op */ u64 base = phys_initrd_start & PAGE_MASK; u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base; /* * We can only add back the initrd memory if we don't end up * with more memory than we can address via the linear mapping. * It is up to the bootloader to position the kernel and the * initrd reasonably close to each other (i.e., within 32 GB of * each other) so that all granule/#levels combinations can * always access both. */ if (WARN(base < memblock_start_of_DRAM() || base + size > memblock_start_of_DRAM() + linear_region_size, "initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) { phys_initrd_size = 0; } else { memblock_add(base, size); memblock_clear_nomap(base, size); memblock_reserve(base, size); } } if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; /* * Use the sanitised version of id_aa64mmfr0_el1 so that linear * map randomization can be enabled by shrinking the IPA space. */ u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); int parange = cpuid_feature_extract_unsigned_field( mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); s64 range = linear_region_size - BIT(id_aa64mmfr0_parange_to_phys_shift(parange)); /* * If the size of the linear region exceeds, by a sufficient * margin, the size of the region that the physical memory can * span, randomize the linear region as well. */ if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) { range /= ARM64_MEMSTART_ALIGN; memstart_addr -= ARM64_MEMSTART_ALIGN * ((range * memstart_offset_seed) >> 16); } } /* * Register the kernel text, kernel data, initrd, and initial * pagetables with memblock. */ memblock_reserve(__pa_symbol(_stext), _end - _stext); if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* the generic initrd code expects virtual addresses */ initrd_start = __phys_to_virt(phys_initrd_start); initrd_end = initrd_start + phys_initrd_size; } early_init_fdt_scan_reserved_mem(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; } void __init bootmem_init(void) { unsigned long min, max; min = PFN_UP(memblock_start_of_DRAM()); max = PFN_DOWN(memblock_end_of_DRAM()); early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT); max_pfn = max_low_pfn = max; min_low_pfn = min; arch_numa_init(); /* * must be done after arch_numa_init() which calls numa_init() to * initialize node_online_map that gets used in hugetlb_cma_reserve() * while allocating required CMA size across online nodes. */ #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) arm64_hugetlb_cma_reserve(); #endif kvm_hyp_reserve(); /* * sparse_init() tries to allocate memory from memblock, so must be * done after the fixed reservations */ sparse_init(); zone_sizes_init(); /* * Reserve the CMA area after arm64_dma_phys_limit was initialised. */ dma_contiguous_reserve(arm64_dma_phys_limit); /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ arch_reserve_crashkernel(); memblock_dump_all(); } /* * mem_init() marks the free areas in the mem_map and tells us how much memory * is free. This is done after various parts of the system have claimed their * memory after the kernel image. */ void __init mem_init(void) { unsigned int flags = SWIOTLB_VERBOSE; bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit); if (is_realm_world()) { swiotlb = true; flags |= SWIOTLB_FORCE; } if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) { /* * If no bouncing needed for ZONE_DMA, reduce the swiotlb * buffer for kmalloc() bouncing to 1MB per 1GB of RAM. */ unsigned long size = DIV_ROUND_UP(memblock_phys_mem_size(), 1024); swiotlb_adjust_size(min(swiotlb_size_or_default(), size)); swiotlb = true; } swiotlb_init(swiotlb, flags); swiotlb_update_mem_attributes(); /* this will put all unused low memory onto the freelists */ memblock_free_all(); /* * Check boundaries twice: Some fundamental inconsistencies can be * detected at build time already. */ #ifdef CONFIG_COMPAT BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64); #endif /* * Selected page table levels should match when derived from * scratch using the virtual address range and page size. */ BUILD_BUG_ON(ARM64_HW_PGTABLE_LEVELS(CONFIG_ARM64_VA_BITS) != CONFIG_PGTABLE_LEVELS); if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; /* * On a machine this small we won't get anywhere without * overcommit, so turn it on by default. */ sysctl_overcommit_memory = OVERCOMMIT_ALWAYS; } } void free_initmem(void) { void *lm_init_begin = lm_alias(__init_begin); void *lm_init_end = lm_alias(__init_end); WARN_ON(!IS_ALIGNED((unsigned long)lm_init_begin, PAGE_SIZE)); WARN_ON(!IS_ALIGNED((unsigned long)lm_init_end, PAGE_SIZE)); /* Delete __init region from memblock.reserved. */ memblock_free(lm_init_begin, lm_init_end - lm_init_begin); free_reserved_area(lm_init_begin, lm_init_end, POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which * is not supported by kallsyms. */ vunmap_range((u64)__init_begin, (u64)__init_end); } void dump_mem_limit(void) { if (memory_limit != PHYS_ADDR_MAX) { pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20); } else { pr_emerg("Memory Limit: none\n"); } } #ifdef CONFIG_EXECMEM static u64 module_direct_base __ro_after_init = 0; static u64 module_plt_base __ro_after_init = 0; /* * Choose a random page-aligned base address for a window of 'size' bytes which * entirely contains the interval [start, end - 1]. */ static u64 __init random_bounding_box(u64 size, u64 start, u64 end) { u64 max_pgoff, pgoff; if ((end - start) >= size) return 0; max_pgoff = (size - (end - start)) / PAGE_SIZE; pgoff = get_random_u32_inclusive(0, max_pgoff); return start - pgoff * PAGE_SIZE; } /* * Modules may directly reference data and text anywhere within the kernel * image and other modules. References using PREL32 relocations have a +/-2G * range, and so we need to ensure that the entire kernel image and all modules * fall within a 2G window such that these are always within range. * * Modules may directly branch to functions and code within the kernel text, * and to functions and code within other modules. These branches will use * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure * that the entire kernel text and all module text falls within a 128M window * such that these are always within range. With PLTs, we can expand this to a * 2G window. * * We chose the 128M region to surround the entire kernel image (rather than * just the text) as using the same bounds for the 128M and 2G regions ensures * by construction that we never select a 128M region that is not a subset of * the 2G region. For very large and unusual kernel configurations this means * we may fall back to PLTs where they could have been avoided, but this keeps * the logic significantly simpler. */ static int __init module_init_limits(void) { u64 kernel_end = (u64)_end; u64 kernel_start = (u64)_text; u64 kernel_size = kernel_end - kernel_start; /* * The default modules region is placed immediately below the kernel * image, and is large enough to use the full 2G relocation range. */ BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END); BUILD_BUG_ON(MODULES_VSIZE < SZ_2G); if (!kaslr_enabled()) { if (kernel_size < SZ_128M) module_direct_base = kernel_end - SZ_128M; if (kernel_size < SZ_2G) module_plt_base = kernel_end - SZ_2G; } else { u64 min = kernel_start; u64 max = kernel_end; if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n"); } else { module_direct_base = random_bounding_box(SZ_128M, min, max); if (module_direct_base) { min = module_direct_base; max = module_direct_base + SZ_128M; } } module_plt_base = random_bounding_box(SZ_2G, min, max); } pr_info("%llu pages in range for non-PLT usage", module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0); pr_info("%llu pages in range for PLT usage", module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0); return 0; } static struct execmem_info execmem_info __ro_after_init; struct execmem_info __init *execmem_arch_setup(void) { unsigned long fallback_start = 0, fallback_end = 0; unsigned long start = 0, end = 0; module_init_limits(); /* * Where possible, prefer to allocate within direct branch range of the * kernel such that no PLTs are necessary. */ if (module_direct_base) { start = module_direct_base; end = module_direct_base + SZ_128M; if (module_plt_base) { fallback_start = module_plt_base; fallback_end = module_plt_base + SZ_2G; } } else if (module_plt_base) { start = module_plt_base; end = module_plt_base + SZ_2G; } execmem_info = (struct execmem_info){ .ranges = { [EXECMEM_DEFAULT] = { .start = start, .end = end, .pgprot = PAGE_KERNEL, .alignment = 1, .fallback_start = fallback_start, .fallback_end = fallback_end, }, [EXECMEM_KPROBES] = { .start = VMALLOC_START, .end = VMALLOC_END, .pgprot = PAGE_KERNEL_ROX, .alignment = 1, }, [EXECMEM_BPF] = { .start = VMALLOC_START, .end = VMALLOC_END, .pgprot = PAGE_KERNEL, .alignment = 1, }, }, }; return &execmem_info; } #endif /* CONFIG_EXECMEM */ |
| 479 479 479 479 35 35 30 477 477 30 35 5 5 5 477 478 30 32 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> static struct kmem_cache *user_ns_cachep __ro_after_init; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } static unsigned long enforced_nproc_rlimit(void) { unsigned long limit = RLIM_INFINITY; /* Is RLIMIT_NPROC currently enforced? */ if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) || (current_user_ns() != &init_user_ns)) limit = rlimit(RLIMIT_NPROC); return limit; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifying that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = security_create_user_ns(new); if (ret < 0) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; ns->ns.ops = &userns_operations; refcount_set(&ns->ns.count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } set_userns_rlimit_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); set_userns_rlimit_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_free_inum(&ns->ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } #if IS_ENABLED(CONFIG_BINFMT_MISC) kfree(ns->binfmt_misc); #endif retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); dec_user_namespaces(ucounts); ns = parent; } while (refcount_dec_and_test(&parent->ns.count)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /* * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; /* == 0 unless used with map_id_range_down() */ }; /* * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /* * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /* * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /* * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) { unsigned idx; u32 first, last; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last) return &map->extent[idx]; } return NULL; } /* * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) { struct idmap_key key; key.map_up = true; key.count = 1; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_up_base(extents, map, id); else extent = map_id_up_max(extents, map, id); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /* * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /* * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup_array(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file * @map_ns: user namespace of the target process * @new_map: requested idmap * * If a process requests mapping parent uid 0 into the new ns, verify that the * process writing the map had the CAP_SETFCAP capability as the target process * will be able to write fscaps that are valid in ancestor user namespaces. * * Return: true if the mapping is allowed, false if not. */ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; struct uid_gid_extent *extent0 = NULL; for (idx = 0; idx < new_map->nr_extents; idx++) { if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent0 = &new_map->extent[idx]; else extent0 = &new_map->forward[idx]; if (extent0->lower_first == 0) break; extent0 = NULL; } if (!extent0) return true; if (map_ns == file_ns) { /* The process unshared its ns and is writing to its own * /proc/self/uid_map. User already has full capabilites in * the new namespace. Verify that the parent had CAP_SETFCAP * when it unshared. * */ if (!file_ns->parent_could_setfcap) return false; } else { /* Process p1 is writing to uid_map of p2, who is in a child * user namespace to p1's. Verify that the opener of the map * file has CAP_SETFCAP against the parent of the new map * namespace */ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) return false; } return true; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certain the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) return false; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also has the appropriate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsset *nsset, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = nsset_cred(nsset); if (!cred) return -EINVAL; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); if (set_cred_ucounts(cred) < 0) return -EINVAL; return 0; } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT); return 0; } subsys_initcall(user_namespaces_init); |
| 89 920 222 60 59 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/uaccess.h * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_UACCESS_H #define __ASM_UACCESS_H #include <asm/alternative.h> #include <asm/kernel-pgtable.h> #include <asm/sysreg.h> /* * User space memory access functions */ #include <linux/bitops.h> #include <linux/kasan-checks.h> #include <linux/string.h> #include <asm/asm-extable.h> #include <asm/cpufeature.h> #include <asm/mmu.h> #include <asm/mte.h> #include <asm/ptrace.h> #include <asm/memory.h> #include <asm/extable.h> static inline int __access_ok(const void __user *ptr, unsigned long size); /* * Test whether a block of memory is a valid user space address. * Returns 1 if the range is valid, 0 otherwise. * * This is equivalent to the following test: * (u65)addr + (u65)size <= (u65)TASK_SIZE_MAX */ static inline int access_ok(const void __user *addr, unsigned long size) { /* * Asynchronous I/O running in a kernel thread does not have the * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag * the user address before checking. */ if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) && (current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR))) addr = untagged_addr(addr); return likely(__access_ok(addr, size)); } #define access_ok access_ok #include <asm-generic/access_ok.h> /* * User access enabling/disabling. */ #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void __uaccess_ttbr0_disable(void) { unsigned long flags, ttbr; local_irq_save(flags); ttbr = read_sysreg(ttbr1_el1); ttbr &= ~TTBR_ASID_MASK; /* reserved_pg_dir placed before swapper_pg_dir */ write_sysreg(ttbr - RESERVED_SWAPPER_OFFSET, ttbr0_el1); /* Set reserved ASID */ write_sysreg(ttbr, ttbr1_el1); isb(); local_irq_restore(flags); } static inline void __uaccess_ttbr0_enable(void) { unsigned long flags, ttbr0, ttbr1; /* * Disable interrupts to avoid preemption between reading the 'ttbr0' * variable and the MSR. A context switch could trigger an ASID * roll-over and an update of 'ttbr0'. */ local_irq_save(flags); ttbr0 = READ_ONCE(current_thread_info()->ttbr0); /* Restore active ASID */ ttbr1 = read_sysreg(ttbr1_el1); ttbr1 &= ~TTBR_ASID_MASK; /* safety measure */ ttbr1 |= ttbr0 & TTBR_ASID_MASK; write_sysreg(ttbr1, ttbr1_el1); /* Restore user page table */ write_sysreg(ttbr0, ttbr0_el1); isb(); local_irq_restore(flags); } static inline bool uaccess_ttbr0_disable(void) { if (!system_uses_ttbr0_pan()) return false; __uaccess_ttbr0_disable(); return true; } static inline bool uaccess_ttbr0_enable(void) { if (!system_uses_ttbr0_pan()) return false; __uaccess_ttbr0_enable(); return true; } #else static inline bool uaccess_ttbr0_disable(void) { return false; } static inline bool uaccess_ttbr0_enable(void) { return false; } #endif static inline void __uaccess_disable_hw_pan(void) { asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)); } static inline void __uaccess_enable_hw_pan(void) { asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)); } static inline void uaccess_disable_privileged(void) { mte_disable_tco(); if (uaccess_ttbr0_disable()) return; __uaccess_enable_hw_pan(); } static inline void uaccess_enable_privileged(void) { mte_enable_tco(); if (uaccess_ttbr0_enable()) return; __uaccess_disable_hw_pan(); } /* * Sanitize a uaccess pointer such that it cannot reach any kernel address. * * Clearing bit 55 ensures the pointer cannot address any portion of the TTBR1 * address range (i.e. any kernel address), and either the pointer falls within * the TTBR0 address range or must cause a fault. */ #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) static inline void __user *__uaccess_mask_ptr(const void __user *ptr) { void __user *safe_ptr; asm volatile( " bic %0, %1, %2\n" : "=r" (safe_ptr) : "r" (ptr), "i" (BIT(55)) ); return safe_ptr; } /* * The "__xxx" versions of the user access functions do not verify the address * space - it must have been done previously with a separate "access_ok()" * call. * * The "__xxx_error" versions set the third argument to -EFAULT if an error * occurs, and leave it unchanged on success. */ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_mem_asm(load, reg, x, addr, label, type) \ asm_goto_output( \ "1: " load " " reg "0, [%1]\n" \ _ASM_EXTABLE_##type##ACCESS(1b, %l2) \ : "=r" (x) \ : "r" (addr) : : label) #else #define __get_mem_asm(load, reg, x, addr, label, type) do { \ int __gma_err = 0; \ asm volatile( \ "1: " load " " reg "1, [%2]\n" \ "2:\n" \ _ASM_EXTABLE_##type##ACCESS_ERR_ZERO(1b, 2b, %w0, %w1) \ : "+r" (__gma_err), "=r" (x) \ : "r" (addr)); \ if (__gma_err) goto label; } while (0) #endif #define __raw_get_mem(ldr, x, ptr, label, type) \ do { \ unsigned long __gu_val; \ switch (sizeof(*(ptr))) { \ case 1: \ __get_mem_asm(ldr "b", "%w", __gu_val, (ptr), label, type); \ break; \ case 2: \ __get_mem_asm(ldr "h", "%w", __gu_val, (ptr), label, type); \ break; \ case 4: \ __get_mem_asm(ldr, "%w", __gu_val, (ptr), label, type); \ break; \ case 8: \ __get_mem_asm(ldr, "%x", __gu_val, (ptr), label, type); \ break; \ default: \ BUILD_BUG(); \ } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) /* * We must not call into the scheduler between uaccess_ttbr0_enable() and * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, * we must evaluate these outside of the critical section. */ #define __raw_get_user(x, ptr, label) \ do { \ __typeof__(*(ptr)) __user *__rgu_ptr = (ptr); \ __typeof__(x) __rgu_val; \ __chk_user_ptr(ptr); \ do { \ __label__ __rgu_failed; \ uaccess_ttbr0_enable(); \ __raw_get_mem("ldtr", __rgu_val, __rgu_ptr, __rgu_failed, U); \ uaccess_ttbr0_disable(); \ (x) = __rgu_val; \ break; \ __rgu_failed: \ uaccess_ttbr0_disable(); \ goto label; \ } while (0); \ } while (0) #define __get_user_error(x, ptr, err) \ do { \ __label__ __gu_failed; \ __typeof__(*(ptr)) __user *__p = (ptr); \ might_fault(); \ if (access_ok(__p, sizeof(*__p))) { \ __p = uaccess_mask_ptr(__p); \ __raw_get_user((x), __p, __gu_failed); \ } else { \ __gu_failed: \ (x) = (__force __typeof__(x))0; (err) = -EFAULT; \ } \ } while (0) #define __get_user(x, ptr) \ ({ \ int __gu_err = 0; \ __get_user_error((x), (ptr), __gu_err); \ __gu_err; \ }) #define get_user __get_user /* * We must not call into the scheduler between __mte_enable_tco_async() and * __mte_disable_tco_async(). As `dst` and `src` may contain blocking * functions, we must evaluate these outside of the critical section. */ #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ __typeof__(dst) __gkn_dst = (dst); \ __typeof__(src) __gkn_src = (src); \ do { \ __label__ __gkn_label; \ \ __mte_enable_tco_async(); \ __raw_get_mem("ldr", *((type *)(__gkn_dst)), \ (__force type *)(__gkn_src), __gkn_label, K); \ __mte_disable_tco_async(); \ break; \ __gkn_label: \ __mte_disable_tco_async(); \ goto err_label; \ } while (0); \ } while (0) #define __put_mem_asm(store, reg, x, addr, label, type) \ asm goto( \ "1: " store " " reg "0, [%1]\n" \ "2:\n" \ _ASM_EXTABLE_##type##ACCESS(1b, %l2) \ : : "rZ" (x), "r" (addr) : : label) #define __raw_put_mem(str, x, ptr, label, type) \ do { \ __typeof__(*(ptr)) __pu_val = (x); \ switch (sizeof(*(ptr))) { \ case 1: \ __put_mem_asm(str "b", "%w", __pu_val, (ptr), label, type); \ break; \ case 2: \ __put_mem_asm(str "h", "%w", __pu_val, (ptr), label, type); \ break; \ case 4: \ __put_mem_asm(str, "%w", __pu_val, (ptr), label, type); \ break; \ case 8: \ __put_mem_asm(str, "%x", __pu_val, (ptr), label, type); \ break; \ default: \ BUILD_BUG(); \ } \ } while (0) /* * We must not call into the scheduler between uaccess_ttbr0_enable() and * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions, * we must evaluate these outside of the critical section. */ #define __raw_put_user(x, ptr, label) \ do { \ __label__ __rpu_failed; \ __typeof__(*(ptr)) __user *__rpu_ptr = (ptr); \ __typeof__(*(ptr)) __rpu_val = (x); \ __chk_user_ptr(__rpu_ptr); \ \ do { \ uaccess_ttbr0_enable(); \ __raw_put_mem("sttr", __rpu_val, __rpu_ptr, __rpu_failed, U); \ uaccess_ttbr0_disable(); \ break; \ __rpu_failed: \ uaccess_ttbr0_disable(); \ goto label; \ } while (0); \ } while (0) #define __put_user_error(x, ptr, err) \ do { \ __label__ __pu_failed; \ __typeof__(*(ptr)) __user *__p = (ptr); \ might_fault(); \ if (access_ok(__p, sizeof(*__p))) { \ __p = uaccess_mask_ptr(__p); \ __raw_put_user((x), __p, __pu_failed); \ } else { \ __pu_failed: \ (err) = -EFAULT; \ } \ } while (0) #define __put_user(x, ptr) \ ({ \ int __pu_err = 0; \ __put_user_error((x), (ptr), __pu_err); \ __pu_err; \ }) #define put_user __put_user /* * We must not call into the scheduler between __mte_enable_tco_async() and * __mte_disable_tco_async(). As `dst` and `src` may contain blocking * functions, we must evaluate these outside of the critical section. */ #define __put_kernel_nofault(dst, src, type, err_label) \ do { \ __typeof__(dst) __pkn_dst = (dst); \ __typeof__(src) __pkn_src = (src); \ \ do { \ __label__ __pkn_err; \ __mte_enable_tco_async(); \ __raw_put_mem("str", *((type *)(__pkn_src)), \ (__force type *)(__pkn_dst), __pkn_err, K); \ __mte_disable_tco_async(); \ break; \ __pkn_err: \ __mte_disable_tco_async(); \ goto err_label; \ } while (0); \ } while(0) extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); #define raw_copy_from_user(to, from, n) \ ({ \ unsigned long __acfu_ret; \ uaccess_ttbr0_enable(); \ __acfu_ret = __arch_copy_from_user((to), \ __uaccess_mask_ptr(from), (n)); \ uaccess_ttbr0_disable(); \ __acfu_ret; \ }) extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); #define raw_copy_to_user(to, from, n) \ ({ \ unsigned long __actu_ret; \ uaccess_ttbr0_enable(); \ __actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to), \ (from), (n)); \ uaccess_ttbr0_disable(); \ __actu_ret; \ }) static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; uaccess_ttbr0_enable(); return 1; } #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() uaccess_ttbr0_disable() #define unsafe_put_user(x, ptr, label) \ __raw_put_mem("sttr", x, uaccess_mask_ptr(ptr), label, U) #define unsafe_get_user(x, ptr, label) \ __raw_get_mem("ldtr", x, uaccess_mask_ptr(ptr), label, U) /* * KCSAN uses these to save and restore ttbr state. * We do not support KCSAN with ARM64_SW_TTBR0_PAN, so * they are no-ops. */ static inline unsigned long user_access_save(void) { return 0; } static inline void user_access_restore(unsigned long enabled) { } /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. */ #define unsafe_copy_loop(dst, src, len, type, label) \ while (len >= sizeof(type)) { \ unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } #define unsafe_copy_to_user(_dst,_src,_len,label) \ do { \ char __user *__ucu_dst = (_dst); \ const char *__ucu_src = (_src); \ size_t __ucu_len = (_len); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { if (access_ok(to, n)) { uaccess_ttbr0_enable(); n = __arch_clear_user(__uaccess_mask_ptr(to), n); uaccess_ttbr0_disable(); } return n; } #define clear_user __clear_user extern long strncpy_from_user(char *dest, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE extern unsigned long __must_check __copy_user_flushcache(void *to, const void __user *from, unsigned long n); static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size); } #endif #ifdef CONFIG_ARCH_HAS_SUBPAGE_FAULTS /* * Return 0 on success, the number of bytes not probed otherwise. */ static inline size_t probe_subpage_writeable(const char __user *uaddr, size_t size) { if (!system_supports_mte()) return 0; return mte_probe_user_range(uaddr, size); } #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ #ifdef CONFIG_ARM64_GCS static inline int gcssttr(unsigned long __user *addr, unsigned long val) { register unsigned long __user *_addr __asm__ ("x0") = addr; register unsigned long _val __asm__ ("x1") = val; int err = 0; /* GCSSTTR x1, x0 */ asm volatile( "1: .inst 0xd91f1c01\n" "2: \n" _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0) : "+r" (err) : "rZ" (_val), "r" (_addr) : "memory"); return err; } static inline void put_user_gcs(unsigned long val, unsigned long __user *addr, int *err) { int ret; if (!access_ok((char __user *)addr, sizeof(u64))) { *err = -EFAULT; return; } uaccess_ttbr0_enable(); ret = gcssttr(addr, val); if (ret != 0) *err = ret; uaccess_ttbr0_disable(); } #endif /* CONFIG_ARM64_GCS */ #endif /* __ASM_UACCESS_H */ |
| 270 269 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork() * * Copyright (C) 2008-2009 Red Hat, Inc. * Authors: * Izik Eidus * Andrea Arcangeli * Chris Wright * Hugh Dickins */ #include <linux/errno.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/cputime.h> #include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/spinlock.h> #include <linux/xxhash.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/memory.h> #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/ksm.h> #include <linux/hashtable.h> #include <linux/freezer.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/pagewalk.h> #include <asm/tlbflush.h> #include "internal.h" #include "mm_slot.h" #define CREATE_TRACE_POINTS #include <trace/events/ksm.h> #ifdef CONFIG_NUMA #define NUMA(x) (x) #define DO_NUMA(x) do { (x); } while (0) #else #define NUMA(x) (0) #define DO_NUMA(x) do { } while (0) #endif typedef u8 rmap_age_t; /** * DOC: Overview * * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: * * In order to reduce excessive scanning, KSM sorts the memory pages by their * contents into a data structure that holds pointers to the pages' locations. * * Since the contents of the pages may change at any moment, KSM cannot just * insert the pages into a normal sorted tree and expect it to find anything. * Therefore KSM uses two data structures - the stable and the unstable tree. * * The stable tree holds pointers to all the merged pages (ksm pages), sorted * by their contents. Because each such page is write-protected, searching on * this tree is fully assured to be working (except when pages are unmapped), * and therefore this tree is called the stable tree. * * The stable tree node includes information required for reverse * mapping from a KSM page to virtual addresses that map this page. * * In order to avoid large latencies of the rmap walks on KSM pages, * KSM maintains two types of nodes in the stable tree: * * * the regular nodes that keep the reverse mapping structures in a * linked list * * the "chains" that link nodes ("dups") that represent the same * write protected memory content, but each "dup" corresponds to a * different KSM page copy of that content * * Internally, the regular nodes, "dups" and "chains" are represented * using the same struct ksm_stable_node structure. * * In addition to the stable tree, KSM uses a second data structure called the * unstable tree: this tree holds pointers to pages which have been found to * be "unchanged for a period of time". The unstable tree sorts these pages * by their contents, but since they are not write-protected, KSM cannot rely * upon the unstable tree to work correctly - the unstable tree is liable to * be corrupted as its contents are modified, and so it is called unstable. * * KSM solves this problem by several techniques: * * 1) The unstable tree is flushed every time KSM completes scanning all * memory areas, and then the tree is rebuilt again from the beginning. * 2) KSM will only insert into the unstable tree, pages whose hash value * has not changed since the previous scan of all memory areas. * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the * colors of the nodes and not on their contents, assuring that even when * the tree gets "corrupted" it won't get out of balance, so scanning time * remains the same (also, searching and inserting nodes in an rbtree uses * the same algorithm, so we have no overhead when we flush and rebuild). * 4) KSM never flushes the stable tree, which means that even if it were to * take 10 attempts to find a page in the unstable tree, once it is found, * it is secured in the stable tree. (When we scan a new page, we first * compare it against the stable tree, and then against the unstable tree.) * * If the merge_across_nodes tunable is unset, then KSM maintains multiple * stable trees and multiple unstable trees: one of each for each NUMA node. */ /** * struct ksm_mm_slot - ksm information per mm that is being scanned * @slot: hash lookup from mm to mm_slot * @rmap_list: head for this mm_slot's singly-linked list of rmap_items */ struct ksm_mm_slot { struct mm_slot slot; struct ksm_rmap_item *rmap_list; }; /** * struct ksm_scan - cursor for scanning * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * @rmap_list: link to the next rmap to be scanned in the rmap_list * @seqnr: count of completed full scans (needed when removing unstable node) * * There is only the one ksm_scan instance of this cursor structure. */ struct ksm_scan { struct ksm_mm_slot *mm_slot; unsigned long address; struct ksm_rmap_item **rmap_list; unsigned long seqnr; }; /** * struct ksm_stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list * @hlist_dup: linked into the stable_node->hlist with a stable_node chain * @list: linked into migrate_nodes, pending placement in the proper node tree * @hlist: hlist head of rmap_items using this ksm page * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) * @chain_prune_time: time of the last full garbage collection * @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN * @nid: NUMA node id of stable tree in which linked (may not match kpfn) */ struct ksm_stable_node { union { struct rb_node node; /* when node of stable tree */ struct { /* when listed for migration */ struct list_head *head; struct { struct hlist_node hlist_dup; struct list_head list; }; }; }; struct hlist_head hlist; union { unsigned long kpfn; unsigned long chain_prune_time; }; /* * STABLE_NODE_CHAIN can be any negative number in * rmap_hlist_len negative range, but better not -1 to be able * to reliably detect underflows. */ #define STABLE_NODE_CHAIN -1024 int rmap_hlist_len; #ifdef CONFIG_NUMA int nid; #endif }; /** * struct ksm_rmap_item - reverse mapping item for virtual addresses * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree * @nid: NUMA node id of unstable tree in which linked (may not match page) * @mm: the memory structure this rmap_item is pointing into * @address: the virtual address this rmap_item tracks (+ flags in low bits) * @oldchecksum: previous checksum of the page at that virtual address * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node * @age: number of scan iterations since creation * @remaining_skips: how many scans to skip */ struct ksm_rmap_item { struct ksm_rmap_item *rmap_list; union { struct anon_vma *anon_vma; /* when stable */ #ifdef CONFIG_NUMA int nid; /* when node of unstable tree */ #endif }; struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ rmap_age_t age; rmap_age_t remaining_skips; union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ struct ksm_stable_node *head; struct hlist_node hlist; }; }; }; #define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */ #define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */ #define STABLE_FLAG 0x200 /* is listed from the stable tree */ /* The stable and unstable tree heads */ static struct rb_root one_stable_tree[1] = { RB_ROOT }; static struct rb_root one_unstable_tree[1] = { RB_ROOT }; static struct rb_root *root_stable_tree = one_stable_tree; static struct rb_root *root_unstable_tree = one_unstable_tree; /* Recently migrated nodes of stable tree, pending proper placement */ static LIST_HEAD(migrate_nodes); #define STABLE_NODE_DUP_HEAD ((struct list_head *)&migrate_nodes.prev) #define MM_SLOTS_HASH_BITS 10 static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct ksm_mm_slot ksm_mm_head = { .slot.mm_node = LIST_HEAD_INIT(ksm_mm_head.slot.mm_node), }; static struct ksm_scan ksm_scan = { .mm_slot = &ksm_mm_head, }; static struct kmem_cache *rmap_item_cache; static struct kmem_cache *stable_node_cache; static struct kmem_cache *mm_slot_cache; /* Default number of pages to scan per batch */ #define DEFAULT_PAGES_TO_SCAN 100 /* The number of pages scanned */ static unsigned long ksm_pages_scanned; /* The number of nodes in the stable tree */ static unsigned long ksm_pages_shared; /* The number of page slots additionally sharing those nodes */ static unsigned long ksm_pages_sharing; /* The number of nodes in the unstable tree */ static unsigned long ksm_pages_unshared; /* The number of rmap_items in use: to calculate pages_volatile */ static unsigned long ksm_rmap_items; /* The number of stable_node chains */ static unsigned long ksm_stable_node_chains; /* The number of stable_node dups linked to the stable_node chains */ static unsigned long ksm_stable_node_dups; /* Delay in pruning stale stable_node_dups in the stable_node_chains */ static unsigned int ksm_stable_node_chains_prune_millisecs = 2000; /* Maximum number of page slots sharing a stable node */ static int ksm_max_page_sharing = 256; /* Number of pages ksmd should scan in one batch */ static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; /* Checksum of an empty (zeroed) page */ static unsigned int zero_checksum __read_mostly; /* Whether to merge empty (zeroed) pages with actual zero pages */ static bool ksm_use_zero_pages __read_mostly; /* Skip pages that couldn't be de-duplicated previously */ /* Default to true at least temporarily, for testing */ static bool ksm_smart_scan = true; /* The number of zero pages which is placed by KSM */ atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; /* Don't scan more than max pages per batch. */ static unsigned long ksm_advisor_max_pages_to_scan = 30000; /* Min CPU for scanning pages per scan */ #define KSM_ADVISOR_MIN_CPU 10 /* Max CPU for scanning pages per scan */ static unsigned int ksm_advisor_max_cpu = 70; /* Target scan time in seconds to analyze all KSM candidate pages. */ static unsigned long ksm_advisor_target_scan_time = 200; /* Exponentially weighted moving average. */ #define EWMA_WEIGHT 30 /** * struct advisor_ctx - metadata for KSM advisor * @start_scan: start time of the current scan * @scan_time: scan time of previous scan * @change: change in percent to pages_to_scan parameter * @cpu_time: cpu time consumed by the ksmd thread in the previous scan */ struct advisor_ctx { ktime_t start_scan; unsigned long scan_time; unsigned long change; unsigned long long cpu_time; }; static struct advisor_ctx advisor_ctx; /* Define different advisor's */ enum ksm_advisor_type { KSM_ADVISOR_NONE, KSM_ADVISOR_SCAN_TIME, }; static enum ksm_advisor_type ksm_advisor; #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ /* At least scan this many pages per batch. */ static unsigned long ksm_advisor_min_pages_to_scan = 500; static void set_advisor_defaults(void) { if (ksm_advisor == KSM_ADVISOR_NONE) { ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; } else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) { advisor_ctx = (const struct advisor_ctx){ 0 }; ksm_thread_pages_to_scan = ksm_advisor_min_pages_to_scan; } } #endif /* CONFIG_SYSFS */ static inline void advisor_start_scan(void) { if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) advisor_ctx.start_scan = ktime_get(); } /* * Use previous scan time if available, otherwise use current scan time as an * approximation for the previous scan time. */ static inline unsigned long prev_scan_time(struct advisor_ctx *ctx, unsigned long scan_time) { return ctx->scan_time ? ctx->scan_time : scan_time; } /* Calculate exponential weighted moving average */ static unsigned long ewma(unsigned long prev, unsigned long curr) { return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100; } /* * The scan time advisor is based on the current scan rate and the target * scan rate. * * new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time) * * To avoid perturbations it calculates a change factor of previous changes. * A new change factor is calculated for each iteration and it uses an * exponentially weighted moving average. The new pages_to_scan value is * multiplied with that change factor: * * new_pages_to_scan *= change facor * * The new_pages_to_scan value is limited by the cpu min and max values. It * calculates the cpu percent for the last scan and calculates the new * estimated cpu percent cost for the next scan. That value is capped by the * cpu min and max setting. * * In addition the new pages_to_scan value is capped by the max and min * limits. */ static void scan_time_advisor(void) { unsigned int cpu_percent; unsigned long cpu_time; unsigned long cpu_time_diff; unsigned long cpu_time_diff_ms; unsigned long pages; unsigned long per_page_cost; unsigned long factor; unsigned long change; unsigned long last_scan_time; unsigned long scan_time; /* Convert scan time to seconds */ scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan), MSEC_PER_SEC); scan_time = scan_time ? scan_time : 1; /* Calculate CPU consumption of ksmd background thread */ cpu_time = task_sched_runtime(current); cpu_time_diff = cpu_time - advisor_ctx.cpu_time; cpu_time_diff_ms = cpu_time_diff / 1000 / 1000; cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000); cpu_percent = cpu_percent ? cpu_percent : 1; last_scan_time = prev_scan_time(&advisor_ctx, scan_time); /* Calculate scan time as percentage of target scan time */ factor = ksm_advisor_target_scan_time * 100 / scan_time; factor = factor ? factor : 1; /* * Calculate scan time as percentage of last scan time and use * exponentially weighted average to smooth it */ change = scan_time * 100 / last_scan_time; change = change ? change : 1; change = ewma(advisor_ctx.change, change); /* Calculate new scan rate based on target scan rate. */ pages = ksm_thread_pages_to_scan * 100 / factor; /* Update pages_to_scan by weighted change percentage. */ pages = pages * change / 100; /* Cap new pages_to_scan value */ per_page_cost = ksm_thread_pages_to_scan / cpu_percent; per_page_cost = per_page_cost ? per_page_cost : 1; pages = min(pages, per_page_cost * ksm_advisor_max_cpu); pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU); pages = min(pages, ksm_advisor_max_pages_to_scan); /* Update advisor context */ advisor_ctx.change = change; advisor_ctx.scan_time = scan_time; advisor_ctx.cpu_time = cpu_time; ksm_thread_pages_to_scan = pages; trace_ksm_advisor(scan_time, pages, cpu_percent); } static void advisor_stop_scan(void) { if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) scan_time_advisor(); } #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; static int ksm_nr_node_ids = 1; #else #define ksm_merge_across_nodes 1U #define ksm_nr_node_ids 1 #endif #define KSM_RUN_STOP 0 #define KSM_RUN_MERGE 1 #define KSM_RUN_UNMERGE 2 #define KSM_RUN_OFFLINE 4 static unsigned long ksm_run = KSM_RUN_STOP; static void wait_while_offlining(void); static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait); static DEFINE_MUTEX(ksm_thread_mutex); static DEFINE_SPINLOCK(ksm_mmlist_lock); static int __init ksm_slab_init(void) { rmap_item_cache = KMEM_CACHE(ksm_rmap_item, 0); if (!rmap_item_cache) goto out; stable_node_cache = KMEM_CACHE(ksm_stable_node, 0); if (!stable_node_cache) goto out_free1; mm_slot_cache = KMEM_CACHE(ksm_mm_slot, 0); if (!mm_slot_cache) goto out_free2; return 0; out_free2: kmem_cache_destroy(stable_node_cache); out_free1: kmem_cache_destroy(rmap_item_cache); out: return -ENOMEM; } static void __init ksm_slab_free(void) { kmem_cache_destroy(mm_slot_cache); kmem_cache_destroy(stable_node_cache); kmem_cache_destroy(rmap_item_cache); mm_slot_cache = NULL; } static __always_inline bool is_stable_node_chain(struct ksm_stable_node *chain) { return chain->rmap_hlist_len == STABLE_NODE_CHAIN; } static __always_inline bool is_stable_node_dup(struct ksm_stable_node *dup) { return dup->head == STABLE_NODE_DUP_HEAD; } static inline void stable_node_chain_add_dup(struct ksm_stable_node *dup, struct ksm_stable_node *chain) { VM_BUG_ON(is_stable_node_dup(dup)); dup->head = STABLE_NODE_DUP_HEAD; VM_BUG_ON(!is_stable_node_chain(chain)); hlist_add_head(&dup->hlist_dup, &chain->hlist); ksm_stable_node_dups++; } static inline void __stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(!is_stable_node_dup(dup)); hlist_del(&dup->hlist_dup); ksm_stable_node_dups--; } static inline void stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(is_stable_node_chain(dup)); if (is_stable_node_dup(dup)) __stable_node_dup_del(dup); else rb_erase(&dup->node, root_stable_tree + NUMA(dup->nid)); #ifdef CONFIG_DEBUG_VM dup->head = NULL; #endif } static inline struct ksm_rmap_item *alloc_rmap_item(void) { struct ksm_rmap_item *rmap_item; rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (rmap_item) ksm_rmap_items++; return rmap_item; } static inline void free_rmap_item(struct ksm_rmap_item *rmap_item) { ksm_rmap_items--; rmap_item->mm->ksm_rmap_items--; rmap_item->mm = NULL; /* debug safety */ kmem_cache_free(rmap_item_cache, rmap_item); } static inline struct ksm_stable_node *alloc_stable_node(void) { /* * The allocation can take too long with GFP_KERNEL when memory is under * pressure, which may lead to hung task warnings. Adding __GFP_HIGH * grants access to memory reserves, helping to avoid this problem. */ return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH); } static inline void free_stable_node(struct ksm_stable_node *stable_node) { VM_BUG_ON(stable_node->rmap_hlist_len && !is_stable_node_chain(stable_node)); kmem_cache_free(stable_node_cache, stable_node); } /* * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's * page tables after it has passed through ksm_exit() - which, if necessary, * takes mmap_lock briefly to serialize against them. ksm_exit() does not set * a special flag: they can just back out as soon as mm_users goes to zero. * ksm_test_exit() is used throughout to make this test for exit: in some * places for correctness, in some places just to avoid unnecessary work. */ static inline bool ksm_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } /* * We use break_ksm to break COW on a ksm page by triggering unsharing, * such that the ksm page will get replaced by an exclusive anonymous page. * * We take great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP * mmap of /dev/mem, where we would not want to touch it. * * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_vma) { vm_fault_t ret = 0; if (lock_vma) vma_start_write(vma); do { bool ksm_page = false; struct folio_walk fw; struct folio *folio; cond_resched(); folio = folio_walk_start(&fw, vma, addr, FW_MIGRATION | FW_ZEROPAGE); if (folio) { /* Small folio implies FW_LEVEL_PTE. */ if (!folio_test_large(folio) && (folio_test_ksm(folio) || is_ksm_zero_pte(fw.pte))) ksm_page = true; folio_walk_end(&fw, vma); } if (!ksm_page) return 0; ret = handle_mm_fault(vma, addr, FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, NULL); } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop until we no longer find a KSM page because * handle_mm_fault() may back out if there's any difficulty e.g. if * pte accessed bit gets updated concurrently. * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's * okay, that truncation will have unmapped the KSM page for us. * * VM_FAULT_OOM: at the time of writing (late July 2009), setting * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the * current task has TIF_MEMDIE set, and will be OOM killed on return * to user; and ksmd, having no mm, would never be chosen for that. * * But if the mm is in a limited mem_cgroup, then the fault may fail * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and * even ksmd can fail in this way - though it's usually breaking ksm * just to undo a merge it made a moment before, so unlikely to oom. * * That's a pity: we might therefore have more kernel pages allocated * than we're counting as nodes in the stable tree; but ksm_do_scan * will retry to break_cow on each pass, so should recover the page * in due course. The important thing is to not let VM_MERGEABLE * be cleared while any such pages might remain in the area. */ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; } static bool vma_ksm_compatible(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | VM_HUGETLB | VM_MIXEDMAP| VM_DROPPABLE)) return false; /* just ignore the advice */ if (vma_is_dax(vma)) return false; #ifdef VM_SAO if (vma->vm_flags & VM_SAO) return false; #endif #ifdef VM_SPARC_ADI if (vma->vm_flags & VM_SPARC_ADI) return false; #endif return true; } static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; if (ksm_test_exit(mm)) return NULL; vma = vma_lookup(mm, addr); if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) return NULL; return vma; } static void break_cow(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; /* * It is not an accident that whenever we want to break COW * to undo, we also need to drop a reference to the anon_vma. */ put_anon_vma(rmap_item->anon_vma); mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (vma) break_ksm(vma, addr, false); mmap_read_unlock(mm); } static struct page *get_mergeable_page(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; struct page *page = NULL; struct folio_walk fw; struct folio *folio; mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (!vma) goto out; folio = folio_walk_start(&fw, vma, addr, 0); if (folio) { if (!folio_is_zone_device(folio) && folio_test_anon(folio)) { folio_get(folio); page = fw.page; } folio_walk_end(&fw, vma); } out: if (page) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } mmap_read_unlock(mm); return page; } /* * This helper is used for getting right index into array of tree roots. * When merge_across_nodes knob is set to 1, there are only two rb-trees for * stable and unstable pages from all nodes with roots in index 0. Otherwise, * every node has its own stable and unstable tree. */ static inline int get_kpfn_nid(unsigned long kpfn) { return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn)); } static struct ksm_stable_node *alloc_stable_node_chain(struct ksm_stable_node *dup, struct rb_root *root) { struct ksm_stable_node *chain = alloc_stable_node(); VM_BUG_ON(is_stable_node_chain(dup)); if (likely(chain)) { INIT_HLIST_HEAD(&chain->hlist); chain->chain_prune_time = jiffies; chain->rmap_hlist_len = STABLE_NODE_CHAIN; #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) chain->nid = NUMA_NO_NODE; /* debug */ #endif ksm_stable_node_chains++; /* * Put the stable node chain in the first dimension of * the stable tree and at the same time remove the old * stable node. */ rb_replace_node(&dup->node, &chain->node, root); /* * Move the old stable node to the second dimension * queued in the hlist_dup. The invariant is that all * dup stable_nodes in the chain->hlist point to pages * that are write protected and have the exact same * content. */ stable_node_chain_add_dup(dup, chain); } return chain; } static inline void free_stable_node_chain(struct ksm_stable_node *chain, struct rb_root *root) { rb_erase(&chain->node, root); free_stable_node(chain); ksm_stable_node_chains--; } static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) { struct ksm_rmap_item *rmap_item; /* check it's not STABLE_NODE_CHAIN or negative */ BUG_ON(stable_node->rmap_hlist_len < 0); hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { if (rmap_item->hlist.next) { ksm_pages_sharing--; trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm); } else { ksm_pages_shared--; } rmap_item->mm->ksm_merging_pages--; VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); rmap_item->address &= PAGE_MASK; cond_resched(); } /* * We need the second aligned pointer of the migrate_nodes * list_head to stay clear from the rb_parent_color union * (aligned and different than any node) and also different * from &migrate_nodes. This will verify that future list.h changes * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it. */ BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); trace_ksm_remove_ksm_page(stable_node->kpfn); if (stable_node->head == &migrate_nodes) list_del(&stable_node->list); else stable_node_dup_del(stable_node); free_stable_node(stable_node); } enum ksm_get_folio_flags { KSM_GET_FOLIO_NOLOCK, KSM_GET_FOLIO_LOCK, KSM_GET_FOLIO_TRYLOCK }; /* * ksm_get_folio: checks if the page indicated by the stable node * is still its ksm page, despite having held no reference to it. * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, * remove the stale node from the stable tree and return NULL. * But beware, the stable node's page might be being migrated. * * You would expect the stable_node to hold a reference to the ksm page. * But if it increments the page's count, swapping out has to wait for * ksmd to come around again before it can free the page, which may take * seconds or even minutes: much too unresponsive. So instead we use a * "keyhole reference": access to the ksm page from the stable node peeps * out through its keyhole to see if that page still holds the right key, * pointing back to this stable node. This relies on freeing a PageAnon * page to reset its page->mapping to NULL, and relies on no other use of * a page to put something that might look like our key in page->mapping. * is on its way to being freed; but it is an anomaly to bear in mind. */ static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node, enum ksm_get_folio_flags flags) { struct folio *folio; void *expected_mapping; unsigned long kpfn; expected_mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ folio = pfn_folio(kpfn); if (READ_ONCE(folio->mapping) != expected_mapping) goto stale; /* * We cannot do anything with the page while its refcount is 0. * Usually 0 means free, or tail of a higher-order page: in which * case this node is no longer referenced, and should be freed; * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; * the same is in reuse_ksm_page() case; but if page is swapcache * in folio_migrate_mapping(), it might still be our page, * in which case it's essential to keep the node. */ while (!folio_try_get(folio)) { /* * Another check for folio->mapping != expected_mapping * would work here too. We have chosen to test the * swapcache flag to optimize the common case, when the * folio is or is about to be freed: the swapcache flag * is cleared (under spin_lock_irq) in the ref_freeze * section of __remove_mapping(); but anon folio->mapping * is reset to NULL later, in free_pages_prepare(). */ if (!folio_test_swapcache(folio)) goto stale; cpu_relax(); } if (READ_ONCE(folio->mapping) != expected_mapping) { folio_put(folio); goto stale; } if (flags == KSM_GET_FOLIO_TRYLOCK) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EBUSY); } } else if (flags == KSM_GET_FOLIO_LOCK) folio_lock(folio); if (flags != KSM_GET_FOLIO_NOLOCK) { if (READ_ONCE(folio->mapping) != expected_mapping) { folio_unlock(folio); folio_put(folio); goto stale; } } return folio; stale: /* * We come here from above when folio->mapping or the swapcache flag * suggests that the node is stale; but it might be under migration. * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); if (READ_ONCE(stable_node->kpfn) != kpfn) goto again; remove_node_from_stable_tree(stable_node); return NULL; } /* * Removing rmap_item from stable or unstable tree. * This function will clean the information from the stable/unstable tree. */ static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item) { if (rmap_item->address & STABLE_FLAG) { struct ksm_stable_node *stable_node; struct folio *folio; stable_node = rmap_item->head; folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) goto out; hlist_del(&rmap_item->hlist); folio_unlock(folio); folio_put(folio); if (!hlist_empty(&stable_node->hlist)) ksm_pages_sharing--; else ksm_pages_shared--; rmap_item->mm->ksm_merging_pages--; VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); rmap_item->head = NULL; rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { unsigned char age; /* * Usually ksmd can and must skip the rb_erase, because * root_unstable_tree was already reset to RB_ROOT. * But be careful when an mm is exiting: do the rb_erase * if this rmap_item was inserted by this scan, rather * than left over from before. */ age = (unsigned char)(ksm_scan.seqnr - rmap_item->address); BUG_ON(age > 1); if (!age) rb_erase(&rmap_item->node, root_unstable_tree + NUMA(rmap_item->nid)); ksm_pages_unshared--; rmap_item->address &= PAGE_MASK; } out: cond_resched(); /* we're called from many long loops */ } static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list) { while (*rmap_list) { struct ksm_rmap_item *rmap_item = *rmap_list; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } } /* * Though it's very tempting to unmerge rmap_items from stable tree rather * than check every pte of a given vma, the locking doesn't quite work for * that - an rmap_item is assigned to the stable tree after inserting ksm * page and upping mmap_lock. Nor does it fit with the way we skip dup'ing * rmap_items from parent to child at fork time (so as not to waste time * if exit comes before the next scan reaches it). * * Similarly, although we'd like to remove rmap_items (so updating counts * and freeing memory) when unmerging an area, it's easier to leave that * to the next pass of ksmd - consider, for example, how ksmd might be * in cmp_and_merge_page on one of the rmap_items we would be removing. */ static int unmerge_ksm_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool lock_vma) { unsigned long addr; int err = 0; for (addr = start; addr < end && !err; addr += PAGE_SIZE) { if (ksm_test_exit(vma->vm_mm)) break; if (signal_pending(current)) err = -ERESTARTSYS; else err = break_ksm(vma, addr, lock_vma); } return err; } static inline struct ksm_stable_node *folio_stable_node(const struct folio *folio) { return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; } static inline struct ksm_stable_node *page_stable_node(struct page *page) { return folio_stable_node(page_folio(page)); } static inline void folio_set_stable_node(struct folio *folio, struct ksm_stable_node *stable_node) { VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio); folio->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); } #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ static int remove_stable_node(struct ksm_stable_node *stable_node) { struct folio *folio; int err; folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) { /* * ksm_get_folio did remove_node_from_stable_tree itself. */ return 0; } /* * Page could be still mapped if this races with __mmput() running in * between ksm_exit() and exit_mmap(). Just refuse to let * merge_across_nodes/max_page_sharing be switched. */ err = -EBUSY; if (!folio_mapped(folio)) { /* * The stable node did not yet appear stale to ksm_get_folio(), * since that allows for an unmapped ksm folio to be recognized * right up until it is freed; but the node is safe to remove. * This folio might be in an LRU cache waiting to be freed, * or it might be in the swapcache (perhaps under writeback), * or it might have been removed from swapcache a moment ago. */ folio_set_stable_node(folio, NULL); remove_node_from_stable_tree(stable_node); err = 0; } folio_unlock(folio); folio_put(folio); return err; } static int remove_stable_node_chain(struct ksm_stable_node *stable_node, struct rb_root *root) { struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { VM_BUG_ON(is_stable_node_dup(stable_node)); if (remove_stable_node(stable_node)) return true; else return false; } hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { VM_BUG_ON(!is_stable_node_dup(dup)); if (remove_stable_node(dup)) return true; } BUG_ON(!hlist_empty(&stable_node->hlist)); free_stable_node_chain(stable_node, root); return false; } static int remove_all_stable_nodes(void) { struct ksm_stable_node *stable_node, *next; int nid; int err = 0; for (nid = 0; nid < ksm_nr_node_ids; nid++) { while (root_stable_tree[nid].rb_node) { stable_node = rb_entry(root_stable_tree[nid].rb_node, struct ksm_stable_node, node); if (remove_stable_node_chain(stable_node, root_stable_tree + nid)) { err = -EBUSY; break; /* proceed to next nid */ } cond_resched(); } } list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (remove_stable_node(stable_node)) err = -EBUSY; cond_resched(); } return err; } static int unmerge_and_remove_all_rmap_items(void) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int err = 0; spin_lock(&ksm_mmlist_lock); slot = list_entry(ksm_mm_head.slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); spin_unlock(&ksm_mmlist_lock); for (mm_slot = ksm_scan.mm_slot; mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) { VMA_ITERATOR(vmi, mm_slot->slot.mm, 0); mm = mm_slot->slot.mm; mmap_read_lock(mm); /* * Exit right away if mm is exiting to avoid lockdep issue in * the maple tree */ if (ksm_test_exit(mm)) goto mm_exiting; for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) continue; err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, false); if (err) goto error; } mm_exiting: remove_trailing_rmap_items(&mm_slot->rmap_list); mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_test_exit(mm)) { hash_del(&mm_slot->slot.hash); list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmdrop(mm); } else spin_unlock(&ksm_mmlist_lock); } /* Clean up stable nodes, but don't worry if some are still busy */ remove_all_stable_nodes(); ksm_scan.seqnr = 0; return 0; error: mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = &ksm_mm_head; spin_unlock(&ksm_mmlist_lock); return err; } #endif /* CONFIG_SYSFS */ static u32 calc_checksum(struct page *page) { u32 checksum; void *addr = kmap_local_page(page); checksum = xxhash(addr, PAGE_SIZE, 0); kunmap_local(addr); return checksum; } static int write_protect_page(struct vm_area_struct *vma, struct folio *folio, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0); int swapped; int err = -EFAULT; struct mmu_notifier_range range; bool anon_exclusive; pte_t entry; if (WARN_ON_ONCE(folio_test_large(folio))) return err; pvmw.address = page_address_in_vma(folio, folio_page(folio, 0), vma); if (pvmw.address == -EFAULT) goto out; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address, pvmw.address + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); if (!page_vma_mapped_walk(&pvmw)) goto out_mn; if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) goto out_unlock; anon_exclusive = PageAnonExclusive(&folio->page); entry = ptep_get(pvmw.pte); if (pte_write(entry) || pte_dirty(entry) || anon_exclusive || mm_tlb_flush_pending(mm)) { swapped = folio_test_swapcache(folio); flush_cache_page(vma, pvmw.address, folio_pfn(folio)); /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make * with the pagecount against the mapcount is racy and * O_DIRECT can happen right after the check. * So we clear the pte and flush the tlb before the check * this assure us that no O_DIRECT can happen after the check * or in the middle of the check. * * No need to notify as we are downgrading page table to read * only not changing it to point to a new page. * * See Documentation/mm/mmu_notifier.rst */ entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* * Check that no O_DIRECT or similar I/O is in progress on the * page */ if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, &folio->page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } if (pte_dirty(entry)) folio_mark_dirty(folio); entry = pte_mkclean(entry); if (pte_write(entry)) entry = pte_wrprotect(entry); set_pte_at(mm, pvmw.address, pvmw.pte, entry); } *orig_pte = entry; err = 0; out_unlock: page_vma_mapped_walk_done(&pvmw); out_mn: mmu_notifier_invalidate_range_end(&range); out: return err; } /** * replace_page - replace page in vma by new ksm page * @vma: vma that holds the pte pointing to page * @page: the page we are replacing by kpage * @kpage: the ksm page we replace page by * @orig_pte: the original value of the pte * * Returns 0 on success, -EFAULT on failure. */ static int replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage, pte_t orig_pte) { struct folio *kfolio = page_folio(kpage); struct mm_struct *mm = vma->vm_mm; struct folio *folio = page_folio(page); pmd_t *pmd; pmd_t pmde; pte_t *ptep; pte_t newpte; spinlock_t *ptl; unsigned long addr; int err = -EFAULT; struct mmu_notifier_range range; addr = page_address_in_vma(folio, page, vma); if (addr == -EFAULT) goto out; pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = pmdp_get_lockless(pmd); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) goto out; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!ptep) goto out_mn; if (!pte_same(ptep_get(ptep), orig_pte)) { pte_unmap_unlock(ptep, ptl); goto out_mn; } VM_BUG_ON_PAGE(PageAnonExclusive(page), page); VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage), kfolio); /* * No need to check ksm_use_zero_pages here: we can only have a * zero_page here if ksm_use_zero_pages was enabled already. */ if (!is_zero_pfn(page_to_pfn(kpage))) { folio_get(kfolio); folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { /* * Use pte_mkdirty to mark the zero page mapped by KSM, and then * we can easily track all KSM-placed zero pages by checking if * the dirty bit in zero page's PTE is set. */ newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); ksm_map_zero_page(mm); /* * We're replacing an anonymous page with a zero page, which is * not anonymous. We need to do proper accounting otherwise we * will get wrong values in /proc, and a BUG message in dmesg * when tearing down the mm. */ dec_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(ptep_get(ptep))); /* * No need to notify as we are replacing a read only page with another * read only page with the same content. * * See Documentation/mm/mmu_notifier.rst */ ptep_clear_flush(vma, addr, ptep); set_pte_at(mm, addr, ptep, newpte); folio_remove_rmap_pte(folio, page, vma); if (!folio_mapped(folio)) folio_free_swap(folio); folio_put(folio); pte_unmap_unlock(ptep, ptl); err = 0; out_mn: mmu_notifier_invalidate_range_end(&range); out: return err; } /* * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page * @page: the PageAnon page that we want to replace with kpage * @kpage: the KSM page that we want to map instead of page, * or NULL the first time when we want to use page as kpage. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_one_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { struct folio *folio = page_folio(page); pte_t orig_pte = __pte(0); int err = -EFAULT; if (page == kpage) /* ksm page forked */ return 0; if (!folio_test_anon(folio)) goto out; /* * We need the folio lock to read a stable swapcache flag in * write_protect_page(). We trylock because we don't want to wait * here - we prefer to continue scanning and merging different * pages, then come back to this page when it is unlocked. */ if (!folio_trylock(folio)) goto out; if (folio_test_large(folio)) { if (split_huge_page(page)) goto out_unlock; folio = page_folio(page); } /* * If this anonymous page is mapped only here, its pte may need * to be write-protected. If it's mapped elsewhere, all of its * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ if (write_protect_page(vma, folio, &orig_pte) == 0) { if (!kpage) { /* * While we hold folio lock, upgrade folio from * anon to a NULL stable_node with the KSM flag set: * stable_tree_insert() will update stable_node. */ folio_set_stable_node(folio, NULL); folio_mark_accessed(folio); /* * Page reclaim just frees a clean folio with no dirty * ptes: make sure that the ksm page would be swapped. */ if (!folio_test_dirty(folio)) folio_mark_dirty(folio); err = 0; } else if (pages_identical(page, kpage)) err = replace_page(vma, page, kpage, orig_pte); } out_unlock: folio_unlock(folio); out: return err; } /* * This function returns 0 if the pages were merged or if they are * no longer merging candidates (e.g., VMA stale), -EFAULT otherwise. */ static int try_to_merge_with_zero_page(struct ksm_rmap_item *rmap_item, struct page *page) { struct mm_struct *mm = rmap_item->mm; int err = -EFAULT; /* * Same checksum as an empty page. We attempt to merge it with the * appropriate zero page if the user enabled this via sysfs. */ if (ksm_use_zero_pages && (rmap_item->oldchecksum == zero_checksum)) { struct vm_area_struct *vma; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (vma) { err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); trace_ksm_merge_one_page( page_to_pfn(ZERO_PAGE(rmap_item->address)), rmap_item, mm, err); } else { /* * If the vma is out of date, we do not need to * continue. */ err = 0; } mmap_read_unlock(mm); } return err; } /* * try_to_merge_with_ksm_page - like try_to_merge_two_pages, * but no new kernel page is allocated: kpage must already be a ksm page. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, struct page *page, struct page *kpage) { struct mm_struct *mm = rmap_item->mm; struct vm_area_struct *vma; int err = -EFAULT; mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out; err = try_to_merge_one_page(vma, page, kpage); if (err) goto out; /* Unstable nid is in union with stable anon_vma: remove first */ remove_rmap_item_from_tree(rmap_item); /* Must get reference to anon_vma while still holding mmap_lock */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); out: mmap_read_unlock(mm); trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), rmap_item, mm, err); return err; } /* * try_to_merge_two_pages - take two identical pages and prepare them * to be merged into one page. * * This function returns the kpage if we successfully merged two identical * pages into one ksm page, NULL otherwise. * * Note that this function upgrades page to ksm page: if one of the pages * is already a ksm page, try_to_merge_with_ksm_page should be used. */ static struct folio *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) { int err; err = try_to_merge_with_ksm_page(rmap_item, page, NULL); if (!err) { err = try_to_merge_with_ksm_page(tree_rmap_item, tree_page, page); /* * If that fails, we have a ksm page with only one pte * pointing to it: so break it. */ if (err) break_cow(rmap_item); } return err ? NULL : page_folio(page); } static __always_inline bool __is_page_sharing_candidate(struct ksm_stable_node *stable_node, int offset) { VM_BUG_ON(stable_node->rmap_hlist_len < 0); /* * Check that at least one mapping still exists, otherwise * there's no much point to merge and share with this * stable_node, as the underlying tree_page of the other * sharer is going to be freed soon. */ return stable_node->rmap_hlist_len && stable_node->rmap_hlist_len + offset < ksm_max_page_sharing; } static __always_inline bool is_page_sharing_candidate(struct ksm_stable_node *stable_node) { return __is_page_sharing_candidate(stable_node, 0); } static struct folio *stable_node_dup(struct ksm_stable_node **_stable_node_dup, struct ksm_stable_node **_stable_node, struct rb_root *root, bool prune_stale_stable_nodes) { struct ksm_stable_node *dup, *found = NULL, *stable_node = *_stable_node; struct hlist_node *hlist_safe; struct folio *folio, *tree_folio = NULL; int found_rmap_hlist_len; if (!prune_stale_stable_nodes || time_before(jiffies, stable_node->chain_prune_time + msecs_to_jiffies( ksm_stable_node_chains_prune_millisecs))) prune_stale_stable_nodes = false; else stable_node->chain_prune_time = jiffies; hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { cond_resched(); /* * We must walk all stable_node_dup to prune the stale * stable nodes during lookup. * * ksm_get_folio can drop the nodes from the * stable_node->hlist if they point to freed pages * (that's why we do a _safe walk). The "dup" * stable_node parameter itself will be freed from * under us if it returns NULL. */ folio = ksm_get_folio(dup, KSM_GET_FOLIO_NOLOCK); if (!folio) continue; /* Pick the best candidate if possible. */ if (!found || (is_page_sharing_candidate(dup) && (!is_page_sharing_candidate(found) || dup->rmap_hlist_len > found_rmap_hlist_len))) { if (found) folio_put(tree_folio); found = dup; found_rmap_hlist_len = found->rmap_hlist_len; tree_folio = folio; /* skip put_page for found candidate */ if (!prune_stale_stable_nodes && is_page_sharing_candidate(found)) break; continue; } folio_put(folio); } if (found) { if (hlist_is_singular_node(&found->hlist_dup, &stable_node->hlist)) { /* * If there's not just one entry it would * corrupt memory, better BUG_ON. In KSM * context with no lock held it's not even * fatal. */ BUG_ON(stable_node->hlist.first->next); /* * There's just one entry and it is below the * deduplication limit so drop the chain. */ rb_replace_node(&stable_node->node, &found->node, root); free_stable_node(stable_node); ksm_stable_node_chains--; ksm_stable_node_dups--; /* * NOTE: the caller depends on the stable_node * to be equal to stable_node_dup if the chain * was collapsed. */ *_stable_node = found; /* * Just for robustness, as stable_node is * otherwise left as a stable pointer, the * compiler shall optimize it away at build * time. */ stable_node = NULL; } else if (stable_node->hlist.first != &found->hlist_dup && __is_page_sharing_candidate(found, 1)) { /* * If the found stable_node dup can accept one * more future merge (in addition to the one * that is underway) and is not at the head of * the chain, put it there so next search will * be quicker in the !prune_stale_stable_nodes * case. * * NOTE: it would be inaccurate to use nr > 1 * instead of checking the hlist.first pointer * directly, because in the * prune_stale_stable_nodes case "nr" isn't * the position of the found dup in the chain, * but the total number of dups in the chain. */ hlist_del(&found->hlist_dup); hlist_add_head(&found->hlist_dup, &stable_node->hlist); } } else { /* Its hlist must be empty if no one found. */ free_stable_node_chain(stable_node, root); } *_stable_node_dup = found; return tree_folio; } /* * Like for ksm_get_folio, this function can free the *_stable_node and * *_stable_node_dup if the returned tree_page is NULL. * * It can also free and overwrite *_stable_node with the found * stable_node_dup if the chain is collapsed (in which case * *_stable_node will be equal to *_stable_node_dup like if the chain * never existed). It's up to the caller to verify tree_page is not * NULL before dereferencing *_stable_node or *_stable_node_dup. * * *_stable_node_dup is really a second output parameter of this * function and will be overwritten in all cases, the caller doesn't * need to initialize it. */ static struct folio *__stable_node_chain(struct ksm_stable_node **_stable_node_dup, struct ksm_stable_node **_stable_node, struct rb_root *root, bool prune_stale_stable_nodes) { struct ksm_stable_node *stable_node = *_stable_node; if (!is_stable_node_chain(stable_node)) { *_stable_node_dup = stable_node; return ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); } return stable_node_dup(_stable_node_dup, _stable_node, root, prune_stale_stable_nodes); } static __always_inline struct folio *chain_prune(struct ksm_stable_node **s_n_d, struct ksm_stable_node **s_n, struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, true); } static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d, struct ksm_stable_node **s_n, struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, false); } /* * stable_tree_search - search for page inside the stable tree * * This function checks if there is a page inside the stable tree * with identical content to the page that we are scanning right now. * * This function returns the stable tree node of identical content if found, * -EBUSY if the stable node's page is being migrated, NULL otherwise. */ static struct folio *stable_tree_search(struct page *page) { int nid; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; struct ksm_stable_node *page_node; struct folio *folio; folio = page_folio(page); page_node = folio_stable_node(folio); if (page_node && page_node->head != &migrate_nodes) { /* ksm page forked */ folio_get(folio); return folio; } nid = get_kpfn_nid(folio_pfn(folio)); root = root_stable_tree + nid; again: new = &root->rb_node; parent = NULL; while (*new) { struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); tree_folio = chain_prune(&stable_node_dup, &stable_node, root); if (!tree_folio) { /* * If we walked over a stale stable_node, * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate * false negative insertions just because some * stable_node was stale. */ goto again; } ret = memcmp_pages(page, &tree_folio->page); folio_put(tree_folio); parent = *new; if (ret < 0) new = &parent->rb_left; else if (ret > 0) new = &parent->rb_right; else { if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); /* * If the mapcount of our migrated KSM folio is * at most 1, we can merge it with another * KSM folio where we know that we have space * for one more mapping without exceeding the * ksm_max_page_sharing limit: see * chain_prune(). This way, we can avoid adding * this stable node to the chain. */ if (folio_mapcount(folio) > 1) goto chain_append; } if (!is_page_sharing_candidate(stable_node_dup)) { /* * If the stable_node is a chain and * we got a payload match in memcmp * but we cannot merge the scanned * page in any of the existing * stable_node dups because they're * all full, we need to wait the * scanned page to find itself a match * in the unstable tree to create a * brand new KSM page to add later to * the dups of this stable_node. */ return NULL; } /* * Lock and unlock the stable_node's page (which * might already have been migrated) so that page * migration is sure to notice its raised count. * It would be more elegant to return stable_node * than kpage, but that involves more changes. */ tree_folio = ksm_get_folio(stable_node_dup, KSM_GET_FOLIO_TRYLOCK); if (PTR_ERR(tree_folio) == -EBUSY) return ERR_PTR(-EBUSY); if (unlikely(!tree_folio)) /* * The tree may have been rebalanced, * so re-evaluate parent and new. */ goto again; folio_unlock(tree_folio); if (get_kpfn_nid(stable_node_dup->kpfn) != NUMA(stable_node_dup->nid)) { folio_put(tree_folio); goto replace; } return tree_folio; } } if (!page_node) return NULL; list_del(&page_node->list); DO_NUMA(page_node->nid = nid); rb_link_node(&page_node->node, parent, new); rb_insert_color(&page_node->node, root); out: if (is_page_sharing_candidate(page_node)) { folio_get(folio); return folio; } else return NULL; replace: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { VM_BUG_ON(is_stable_node_chain(stable_node_dup)); VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* there is no chain */ if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); rb_replace_node(&stable_node_dup->node, &page_node->node, root); if (is_page_sharing_candidate(page_node)) folio_get(folio); else folio = NULL; } else { rb_erase(&stable_node_dup->node, root); folio = NULL; } } else { VM_BUG_ON(!is_stable_node_chain(stable_node)); __stable_node_dup_del(stable_node_dup); if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); if (is_page_sharing_candidate(page_node)) folio_get(folio); else folio = NULL; } else { folio = NULL; } } stable_node_dup->head = &migrate_nodes; list_add(&stable_node_dup->list, stable_node_dup->head); return folio; chain_append: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* chain is missing so create it */ stable_node = alloc_stable_node_chain(stable_node_dup, root); if (!stable_node) return NULL; } /* * Add this stable_node dup that was * migrated to the stable_node chain * of the current nid for this page * content. */ VM_BUG_ON(!is_stable_node_dup(stable_node_dup)); VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); goto out; } /* * stable_tree_insert - insert stable tree node pointing to new ksm page * into the stable tree. * * This function returns the stable tree node just allocated on success, * NULL otherwise. */ static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio) { int nid; unsigned long kpfn; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; bool need_chain = false; kpfn = folio_pfn(kfolio); nid = get_kpfn_nid(kpfn); root = root_stable_tree + nid; again: parent = NULL; new = &root->rb_node; while (*new) { struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); tree_folio = chain(&stable_node_dup, &stable_node, root); if (!tree_folio) { /* * If we walked over a stale stable_node, * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate * false negative insertions just because some * stable_node was stale. */ goto again; } ret = memcmp_pages(&kfolio->page, &tree_folio->page); folio_put(tree_folio); parent = *new; if (ret < 0) new = &parent->rb_left; else if (ret > 0) new = &parent->rb_right; else { need_chain = true; break; } } stable_node_dup = alloc_stable_node(); if (!stable_node_dup) return NULL; INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { rb_link_node(&stable_node_dup->node, parent, new); rb_insert_color(&stable_node_dup->node, root); } else { if (!is_stable_node_chain(stable_node)) { struct ksm_stable_node *orig = stable_node; /* chain is missing so create it */ stable_node = alloc_stable_node_chain(orig, root); if (!stable_node) { free_stable_node(stable_node_dup); return NULL; } } stable_node_chain_add_dup(stable_node_dup, stable_node); } folio_set_stable_node(kfolio, stable_node_dup); return stable_node_dup; } /* * unstable_tree_search_insert - search for identical page, * else insert rmap_item into the unstable tree. * * This function searches for a page in the unstable tree identical to the * page currently being scanned; and if no identical page is found in the * tree, we insert rmap_item as a new object into the unstable tree. * * This function returns pointer to rmap_item found to be identical * to the currently scanned page, NULL otherwise. * * This function does both searching and inserting, because they share * the same walking algorithm in an rbtree. */ static struct ksm_rmap_item *unstable_tree_search_insert(struct ksm_rmap_item *rmap_item, struct page *page, struct page **tree_pagep) { struct rb_node **new; struct rb_root *root; struct rb_node *parent = NULL; int nid; nid = get_kpfn_nid(page_to_pfn(page)); root = root_unstable_tree + nid; new = &root->rb_node; while (*new) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page; int ret; cond_resched(); tree_rmap_item = rb_entry(*new, struct ksm_rmap_item, node); tree_page = get_mergeable_page(tree_rmap_item); if (!tree_page) return NULL; /* * Don't substitute a ksm page for a forked page. */ if (page == tree_page) { put_page(tree_page); return NULL; } ret = memcmp_pages(page, tree_page); parent = *new; if (ret < 0) { put_page(tree_page); new = &parent->rb_left; } else if (ret > 0) { put_page(tree_page); new = &parent->rb_right; } else if (!ksm_merge_across_nodes && page_to_nid(tree_page) != nid) { /* * If tree_page has been migrated to another NUMA node, * it will be flushed out and put in the right unstable * tree next time: only merge with it when across_nodes. */ put_page(tree_page); return NULL; } else { *tree_pagep = tree_page; return tree_rmap_item; } } rmap_item->address |= UNSTABLE_FLAG; rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK); DO_NUMA(rmap_item->nid = nid); rb_link_node(&rmap_item->node, parent, new); rb_insert_color(&rmap_item->node, root); ksm_pages_unshared++; return NULL; } /* * stable_tree_append - add another rmap_item to the linked list of * rmap_items hanging off a given node of the stable tree, all sharing * the same ksm page. */ static void stable_tree_append(struct ksm_rmap_item *rmap_item, struct ksm_stable_node *stable_node, bool max_page_sharing_bypass) { /* * rmap won't find this mapping if we don't insert the * rmap_item in the right stable_node * duplicate. page_migration could break later if rmap breaks, * so we can as well crash here. We really need to check for * rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check * for other negative values as an underflow if detected here * for the first time (and not when decreasing rmap_hlist_len) * would be sign of memory corruption in the stable_node. */ BUG_ON(stable_node->rmap_hlist_len < 0); stable_node->rmap_hlist_len++; if (!max_page_sharing_bypass) /* possibly non fatal but unexpected overflow, only warn */ WARN_ON_ONCE(stable_node->rmap_hlist_len > ksm_max_page_sharing); rmap_item->head = stable_node; rmap_item->address |= STABLE_FLAG; hlist_add_head(&rmap_item->hlist, &stable_node->hlist); if (rmap_item->hlist.next) ksm_pages_sharing++; else ksm_pages_shared++; rmap_item->mm->ksm_merging_pages++; } /* * cmp_and_merge_page - first see if page can be merged into the stable tree; * if not, compare checksum to previous and if it's the same, see if page can * be inserted into the unstable tree, or merged with a page already there and * both transferred to the stable tree. * * @page: the page that we are searching identical page to. * @rmap_item: the reverse mapping into the virtual address of this page */ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct ksm_stable_node *stable_node; struct folio *kfolio; unsigned int checksum; int err; bool max_page_sharing_bypass = false; stable_node = page_stable_node(page); if (stable_node) { if (stable_node->head != &migrate_nodes && get_kpfn_nid(READ_ONCE(stable_node->kpfn)) != NUMA(stable_node->nid)) { stable_node_dup_del(stable_node); stable_node->head = &migrate_nodes; list_add(&stable_node->list, stable_node->head); } if (stable_node->head != &migrate_nodes && rmap_item->head == stable_node) return; /* * If it's a KSM fork, allow it to go over the sharing limit * without warnings. */ if (!is_page_sharing_candidate(stable_node)) max_page_sharing_bypass = true; } else { remove_rmap_item_from_tree(rmap_item); /* * If the hash value of the page has changed from the last time * we calculated it, this page is changing frequently: therefore we * don't want to insert it in the unstable tree, and we don't want * to waste our time searching for something identical to it there. */ checksum = calc_checksum(page); if (rmap_item->oldchecksum != checksum) { rmap_item->oldchecksum = checksum; return; } if (!try_to_merge_with_zero_page(rmap_item, page)) return; } /* Start by searching for the folio in the stable tree */ kfolio = stable_tree_search(page); if (&kfolio->page == page && rmap_item->head == stable_node) { folio_put(kfolio); return; } remove_rmap_item_from_tree(rmap_item); if (kfolio) { if (kfolio == ERR_PTR(-EBUSY)) return; err = try_to_merge_with_ksm_page(rmap_item, page, &kfolio->page); if (!err) { /* * The page was successfully merged: * add its rmap_item to the stable tree. */ folio_lock(kfolio); stable_tree_append(rmap_item, folio_stable_node(kfolio), max_page_sharing_bypass); folio_unlock(kfolio); } folio_put(kfolio); return; } tree_rmap_item = unstable_tree_search_insert(rmap_item, page, &tree_page); if (tree_rmap_item) { bool split; kfolio = try_to_merge_two_pages(rmap_item, page, tree_rmap_item, tree_page); /* * If both pages we tried to merge belong to the same compound * page, then we actually ended up increasing the reference * count of the same compound page twice, and split_huge_page * failed. * Here we set a flag if that happened, and we use it later to * try split_huge_page again. Since we call put_page right * afterwards, the reference count will be correct and * split_huge_page should succeed. */ split = PageTransCompound(page) && compound_head(page) == compound_head(tree_page); put_page(tree_page); if (kfolio) { /* * The pages were successfully merged: insert new * node in the stable tree and add both rmap_items. */ folio_lock(kfolio); stable_node = stable_tree_insert(kfolio); if (stable_node) { stable_tree_append(tree_rmap_item, stable_node, false); stable_tree_append(rmap_item, stable_node, false); } folio_unlock(kfolio); /* * If we fail to insert the page into the stable tree, * we will have 2 virtual addresses that are pointing * to a ksm page left outside the stable tree, * in which case we need to break_cow on both. */ if (!stable_node) { break_cow(tree_rmap_item); break_cow(rmap_item); } } else if (split) { /* * We are here if we tried to merge two pages and * failed because they both belonged to the same * compound page. We will split the page now, but no * merging will take place. * We do not want to add the cost of a full lock; if * the page is locked, it is better to skip it and * perhaps try again later. */ if (!trylock_page(page)) return; split_huge_page(page); unlock_page(page); } } } static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot, struct ksm_rmap_item **rmap_list, unsigned long addr) { struct ksm_rmap_item *rmap_item; while (*rmap_list) { rmap_item = *rmap_list; if ((rmap_item->address & PAGE_MASK) == addr) return rmap_item; if (rmap_item->address > addr) break; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } rmap_item = alloc_rmap_item(); if (rmap_item) { /* It has already been zeroed */ rmap_item->mm = mm_slot->slot.mm; rmap_item->mm->ksm_rmap_items++; rmap_item->address = addr; rmap_item->rmap_list = *rmap_list; *rmap_list = rmap_item; } return rmap_item; } /* * Calculate skip age for the ksm page age. The age determines how often * de-duplicating has already been tried unsuccessfully. If the age is * smaller, the scanning of this page is skipped for less scans. * * @age: rmap_item age of page */ static unsigned int skip_age(rmap_age_t age) { if (age <= 3) return 1; if (age <= 5) return 2; if (age <= 8) return 4; return 8; } /* * Determines if a page should be skipped for the current scan. * * @folio: folio containing the page to check * @rmap_item: associated rmap_item of page */ static bool should_skip_rmap_item(struct folio *folio, struct ksm_rmap_item *rmap_item) { rmap_age_t age; if (!ksm_smart_scan) return false; /* * Never skip pages that are already KSM; pages cmp_and_merge_page() * will essentially ignore them, but we still have to process them * properly. */ if (folio_test_ksm(folio)) return false; age = rmap_item->age; if (age != U8_MAX) rmap_item->age++; /* * Smaller ages are not skipped, they need to get a chance to go * through the different phases of the KSM merging. */ if (age < 3) return false; /* * Are we still allowed to skip? If not, then don't skip it * and determine how much more often we are allowed to skip next. */ if (!rmap_item->remaining_skips) { rmap_item->remaining_skips = skip_age(age); return false; } /* Skip this page */ ksm_pages_skipped++; rmap_item->remaining_skips--; remove_rmap_item_from_tree(rmap_item); return true; } static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct vm_area_struct *vma; struct ksm_rmap_item *rmap_item; struct vma_iterator vmi; int nid; if (list_empty(&ksm_mm_head.slot.mm_node)) return NULL; mm_slot = ksm_scan.mm_slot; if (mm_slot == &ksm_mm_head) { advisor_start_scan(); trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items); /* * A number of pages can hang around indefinitely in per-cpu * LRU cache, raised page count preventing write_protect_page * from merging them. Though it doesn't really matter much, * it is puzzling to see some stuck in pages_volatile until * other activity jostles them out, and they also prevented * LTP's KSM test from succeeding deterministically; so drain * them here (here rather than on entry to ksm_do_scan(), * so we don't IPI too often when pages_to_scan is set low). */ lru_add_drain_all(); /* * Whereas stale stable_nodes on the stable_tree itself * get pruned in the regular course of stable_tree_search(), * those moved out to the migrate_nodes list can accumulate: * so prune them once before each full scan. */ if (!ksm_merge_across_nodes) { struct ksm_stable_node *stable_node, *next; struct folio *folio; list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); if (folio) folio_put(folio); cond_resched(); } } for (nid = 0; nid < ksm_nr_node_ids; nid++) root_unstable_tree[nid] = RB_ROOT; spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); ksm_scan.mm_slot = mm_slot; spin_unlock(&ksm_mmlist_lock); /* * Although we tested list_empty() above, a racing __ksm_exit * of the last mm on the list may have removed it since then. */ if (mm_slot == &ksm_mm_head) return NULL; next_mm: ksm_scan.address = 0; ksm_scan.rmap_list = &mm_slot->rmap_list; } slot = &mm_slot->slot; mm = slot->mm; vma_iter_init(&vmi, mm, ksm_scan.address); mmap_read_lock(mm); if (ksm_test_exit(mm)) goto no_vmas; for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE)) continue; if (ksm_scan.address < vma->vm_start) ksm_scan.address = vma->vm_start; if (!vma->anon_vma) ksm_scan.address = vma->vm_end; while (ksm_scan.address < vma->vm_end) { struct page *tmp_page = NULL; struct folio_walk fw; struct folio *folio; if (ksm_test_exit(mm)) break; folio = folio_walk_start(&fw, vma, ksm_scan.address, 0); if (folio) { if (!folio_is_zone_device(folio) && folio_test_anon(folio)) { folio_get(folio); tmp_page = fw.page; } folio_walk_end(&fw, vma); } if (tmp_page) { flush_anon_page(vma, tmp_page, ksm_scan.address); flush_dcache_page(tmp_page); rmap_item = get_next_rmap_item(mm_slot, ksm_scan.rmap_list, ksm_scan.address); if (rmap_item) { ksm_scan.rmap_list = &rmap_item->rmap_list; if (should_skip_rmap_item(folio, rmap_item)) { folio_put(folio); goto next_page; } ksm_scan.address += PAGE_SIZE; *page = tmp_page; } else { folio_put(folio); } mmap_read_unlock(mm); return rmap_item; } next_page: ksm_scan.address += PAGE_SIZE; cond_resched(); } } if (ksm_test_exit(mm)) { no_vmas: ksm_scan.address = 0; ksm_scan.rmap_list = &mm_slot->rmap_list; } /* * Nuke all the rmap_items that are above this current rmap: * because there were no VM_MERGEABLE vmas with such addresses. */ remove_trailing_rmap_items(ksm_scan.rmap_list); spin_lock(&ksm_mmlist_lock); slot = list_entry(mm_slot->slot.mm_node.next, struct mm_slot, mm_node); ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_scan.address == 0) { /* * We've completed a full scan of all vmas, holding mmap_lock * throughout, and found no VM_MERGEABLE: so do the same as * __ksm_exit does to remove this mm from all our lists now. * This applies either when cleaning up after __ksm_exit * (but beware: we can reach here even before __ksm_exit), * or when all VM_MERGEABLE areas have been unmapped (and * mmap_lock then protects against race with MADV_MERGEABLE). */ hash_del(&mm_slot->slot.hash); list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmap_read_unlock(mm); mmdrop(mm); } else { mmap_read_unlock(mm); /* * mmap_read_unlock(mm) first because after * spin_unlock(&ksm_mmlist_lock) run, the "mm" may * already have been freed under us by __ksm_exit() * because the "mm_slot" is still hashed and * ksm_scan.mm_slot doesn't point to it anymore. */ spin_unlock(&ksm_mmlist_lock); } /* Repeat until we've completed scanning the whole list */ mm_slot = ksm_scan.mm_slot; if (mm_slot != &ksm_mm_head) goto next_mm; advisor_stop_scan(); trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items); ksm_scan.seqnr++; return NULL; } /** * ksm_do_scan - the ksm scanner main worker function. * @scan_npages: number of pages we want to scan before we return. */ static void ksm_do_scan(unsigned int scan_npages) { struct ksm_rmap_item *rmap_item; struct page *page; while (scan_npages-- && likely(!freezing(current))) { cond_resched(); rmap_item = scan_get_next_rmap_item(&page); if (!rmap_item) return; cmp_and_merge_page(page, rmap_item); put_page(page); ksm_pages_scanned++; } } static int ksmd_should_run(void) { return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node); } static int ksm_scan_thread(void *nothing) { unsigned int sleep_ms; set_freezable(); set_user_nice(current, 5); while (!kthread_should_stop()) { mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksmd_should_run()) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); if (ksmd_should_run()) { sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs); wait_event_freezable_timeout(ksm_iter_wait, sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), msecs_to_jiffies(sleep_ms)); } else { wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); } } return 0; } static void __ksm_add_vma(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; if (vm_flags & VM_MERGEABLE) return; if (vma_ksm_compatible(vma)) vm_flags_set(vma, VM_MERGEABLE); } static int __ksm_del_vma(struct vm_area_struct *vma) { int err; if (!(vma->vm_flags & VM_MERGEABLE)) return 0; if (vma->anon_vma) { err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end, true); if (err) return err; } vm_flags_clear(vma, VM_MERGEABLE); return 0; } /** * ksm_add_vma - Mark vma as mergeable if compatible * * @vma: Pointer to vma */ void ksm_add_vma(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) __ksm_add_vma(vma); } static void ksm_add_vmas(struct mm_struct *mm) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) __ksm_add_vma(vma); } static int ksm_del_vmas(struct mm_struct *mm) { struct vm_area_struct *vma; int err; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) { err = __ksm_del_vma(vma); if (err) return err; } return 0; } /** * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all * compatible VMA's * * @mm: Pointer to mm * * Returns 0 on success, otherwise error code */ int ksm_enable_merge_any(struct mm_struct *mm) { int err; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return 0; if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); if (err) return err; } set_bit(MMF_VM_MERGE_ANY, &mm->flags); ksm_add_vmas(mm); return 0; } /** * ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm, * previously enabled via ksm_enable_merge_any(). * * Disabling merging implies unmerging any merged pages, like setting * MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and * merging on all compatible VMA's remains enabled. * * @mm: Pointer to mm * * Returns 0 on success, otherwise error code */ int ksm_disable_merge_any(struct mm_struct *mm) { int err; if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return 0; err = ksm_del_vmas(mm); if (err) { ksm_add_vmas(mm); return err; } clear_bit(MMF_VM_MERGE_ANY, &mm->flags); return 0; } int ksm_disable(struct mm_struct *mm) { mmap_assert_write_locked(mm); if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) return 0; if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return ksm_disable_merge_any(mm); return ksm_del_vmas(mm); } int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { struct mm_struct *mm = vma->vm_mm; int err; switch (advice) { case MADV_MERGEABLE: if (vma->vm_flags & VM_MERGEABLE) return 0; if (!vma_ksm_compatible(vma)) return 0; if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); if (err) return err; } *vm_flags |= VM_MERGEABLE; break; case MADV_UNMERGEABLE: if (!(*vm_flags & VM_MERGEABLE)) return 0; /* just ignore the advice */ if (vma->anon_vma) { err = unmerge_ksm_pages(vma, start, end, true); if (err) return err; } *vm_flags &= ~VM_MERGEABLE; break; } return 0; } EXPORT_SYMBOL_GPL(ksm_madvise); int __ksm_enter(struct mm_struct *mm) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; int needs_wakeup; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return -ENOMEM; slot = &mm_slot->slot; /* Check ksm_run too? Would need tighter locking */ needs_wakeup = list_empty(&ksm_mm_head.slot.mm_node); spin_lock(&ksm_mmlist_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * When KSM_RUN_MERGE (or KSM_RUN_STOP), * insert just behind the scanning cursor, to let the area settle * down a little; when fork is followed by immediate exec, we don't * want ksmd to waste time setting up and tearing down an rmap_list. * * But when KSM_RUN_UNMERGE, it's important to insert ahead of its * scanning cursor, otherwise KSM pages in newly forked mms will be * missed: then we might as well insert at the end of the list. */ if (ksm_run & KSM_RUN_UNMERGE) list_add_tail(&slot->mm_node, &ksm_mm_head.slot.mm_node); else list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); set_bit(MMF_VM_MERGEABLE, &mm->flags); mmgrab(mm); if (needs_wakeup) wake_up_interruptible(&ksm_thread_wait); trace_ksm_enter(mm); return 0; } void __ksm_exit(struct mm_struct *mm) { struct ksm_mm_slot *mm_slot; struct mm_slot *slot; int easy_to_free = 0; /* * This process is exiting: if it's straightforward (as is the * case when ksmd was never running), free mm_slot immediately. * But if it's at the cursor or has rmap_items linked to it, use * mmap_lock to synchronize with any break_cows before pagetables * are freed, and leave the mm_slot on the list for ksmd to free. * Beware: ksm may already have noticed it exiting and freed the slot. */ spin_lock(&ksm_mmlist_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (mm_slot && ksm_scan.mm_slot != mm_slot) { if (!mm_slot->rmap_list) { hash_del(&slot->hash); list_del(&slot->mm_node); easy_to_free = 1; } else { list_move(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); } } spin_unlock(&ksm_mmlist_lock); if (easy_to_free) { mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGE_ANY, &mm->flags); clear_bit(MMF_VM_MERGEABLE, &mm->flags); mmdrop(mm); } else if (mm_slot) { mmap_write_lock(mm); mmap_write_unlock(mm); } trace_ksm_exit(mm); } struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { struct page *page = folio_page(folio, 0); struct anon_vma *anon_vma = folio_anon_vma(folio); struct folio *new_folio; if (folio_test_large(folio)) return folio; if (folio_test_ksm(folio)) { if (folio_stable_node(folio) && !(ksm_run & KSM_RUN_UNMERGE)) return folio; /* no need to copy it */ } else if (!anon_vma) { return folio; /* no need to copy it */ } else if (folio->index == linear_page_index(vma, addr) && anon_vma->root == vma->anon_vma->root) { return folio; /* still no need to copy it */ } if (PageHWPoison(page)) return ERR_PTR(-EHWPOISON); if (!folio_test_uptodate(folio)) return folio; /* let do_swap_page report the error */ new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (new_folio && mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) { folio_put(new_folio); new_folio = NULL; } if (new_folio) { if (copy_mc_user_highpage(folio_page(new_folio, 0), page, addr, vma)) { folio_put(new_folio); return ERR_PTR(-EHWPOISON); } folio_set_dirty(new_folio); __folio_mark_uptodate(new_folio); __folio_set_locked(new_folio); #ifdef CONFIG_SWAP count_vm_event(KSM_SWPIN_COPY); #endif } return new_folio; } void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; int search_new_forks = 0; VM_BUG_ON_FOLIO(!folio_test_ksm(folio), folio); /* * Rely on the page lock to protect against concurrent modifications * to that page's node of the stable tree. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); stable_node = folio_stable_node(folio); if (!stable_node) return; again: hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *anon_vma = rmap_item->anon_vma; struct anon_vma_chain *vmac; struct vm_area_struct *vma; cond_resched(); if (!anon_vma_trylock_read(anon_vma)) { if (rwc->try_lock) { rwc->contended = true; return; } anon_vma_lock_read(anon_vma); } anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, 0, ULONG_MAX) { unsigned long addr; cond_resched(); vma = vmac->vma; /* Ignore the stable/unstable/sqnr flags */ addr = rmap_item->address & PAGE_MASK; if (addr < vma->vm_start || addr >= vma->vm_end) continue; /* * Initially we examine only the vma which covers this * rmap_item; but later, if there is still work to do, * we examine covering vmas in other mms: in case they * were forked from the original since ksmd passed. */ if ((rmap_item->mm == vma->vm_mm) == search_new_forks) continue; if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, addr, rwc->arg)) { anon_vma_unlock_read(anon_vma); return; } if (rwc->done && rwc->done(folio)) { anon_vma_unlock_read(anon_vma); return; } } anon_vma_unlock_read(anon_vma); } if (!search_new_forks++) goto again; } #ifdef CONFIG_MEMORY_FAILURE /* * Collect processes when the error hit an ksm page. */ void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; struct vm_area_struct *vma; struct task_struct *tsk; stable_node = folio_stable_node(folio); if (!stable_node) return; hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { struct anon_vma *av = rmap_item->anon_vma; anon_vma_lock_read(av); rcu_read_lock(); for_each_process(tsk) { struct anon_vma_chain *vmac; unsigned long addr; struct task_struct *t = task_early_kill(tsk, force_early); if (!t) continue; anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0, ULONG_MAX) { vma = vmac->vma; if (vma->vm_mm == t->mm) { addr = rmap_item->address & PAGE_MASK; add_to_kill_ksm(t, page, vma, to_kill, addr); } } } rcu_read_unlock(); anon_vma_unlock_read(av); } } #endif #ifdef CONFIG_MIGRATION void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { struct ksm_stable_node *stable_node; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio); stable_node = folio_stable_node(folio); if (stable_node) { VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio); stable_node->kpfn = folio_pfn(newfolio); /* * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible * to ksm_get_folio() before it can see that folio->mapping * has gone stale (or that the swapcache flag has been cleared). */ smp_wmb(); folio_set_stable_node(folio, NULL); } } #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_MEMORY_HOTREMOVE static void wait_while_offlining(void) { while (ksm_run & KSM_RUN_OFFLINE) { mutex_unlock(&ksm_thread_mutex); wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE), TASK_UNINTERRUPTIBLE); mutex_lock(&ksm_thread_mutex); } } static bool stable_node_dup_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) { /* * Don't ksm_get_folio, page has already gone: * which is why we keep kpfn instead of page* */ remove_node_from_stable_tree(stable_node); return true; } return false; } static bool stable_node_chain_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn, struct rb_root *root) { struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { VM_BUG_ON(is_stable_node_dup(stable_node)); return stable_node_dup_remove_range(stable_node, start_pfn, end_pfn); } hlist_for_each_entry_safe(dup, hlist_safe, &stable_node->hlist, hlist_dup) { VM_BUG_ON(!is_stable_node_dup(dup)); stable_node_dup_remove_range(dup, start_pfn, end_pfn); } if (hlist_empty(&stable_node->hlist)) { free_stable_node_chain(stable_node, root); return true; /* notify caller that tree was rebalanced */ } else return false; } static void ksm_check_stable_tree(unsigned long start_pfn, unsigned long end_pfn) { struct ksm_stable_node *stable_node, *next; struct rb_node *node; int nid; for (nid = 0; nid < ksm_nr_node_ids; nid++) { node = rb_first(root_stable_tree + nid); while (node) { stable_node = rb_entry(node, struct ksm_stable_node, node); if (stable_node_chain_remove_range(stable_node, start_pfn, end_pfn, root_stable_tree + nid)) node = rb_first(root_stable_tree + nid); else node = rb_next(node); cond_resched(); } } list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) remove_node_from_stable_tree(stable_node); cond_resched(); } } static int ksm_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; switch (action) { case MEM_GOING_OFFLINE: /* * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() * and remove_all_stable_nodes() while memory is going offline: * it is unsafe for them to touch the stable tree at this time. * But unmerge_ksm_pages(), rmap lookups and other entry points * which do not need the ksm_thread_mutex are all safe. */ mutex_lock(&ksm_thread_mutex); ksm_run |= KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); break; case MEM_OFFLINE: /* * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct * pages which have been offlined: prune those from the tree, * otherwise ksm_get_folio() might later try to access a * non-existent struct page. */ ksm_check_stable_tree(mn->start_pfn, mn->start_pfn + mn->nr_pages); fallthrough; case MEM_CANCEL_OFFLINE: mutex_lock(&ksm_thread_mutex); ksm_run &= ~KSM_RUN_OFFLINE; mutex_unlock(&ksm_thread_mutex); smp_mb(); /* wake_up_bit advises this */ wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE)); break; } return NOTIFY_OK; } #else static void wait_while_offlining(void) { } #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_PROC_FS /* * The process is mergeable only if any VMA is currently * applicable to KSM. * * The mmap lock must be held in read mode. */ bool ksm_process_mergeable(struct mm_struct *mm) { struct vm_area_struct *vma; mmap_assert_locked(mm); VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) if (vma->vm_flags & VM_MERGEABLE) return true; return false; } long ksm_process_profit(struct mm_struct *mm) { return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSFS /* * This all compiles without CONFIG_SYSFS, but is a waste of space. */ #define KSM_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define KSM_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static ssize_t sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_thread_sleep_millisecs); } static ssize_t sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; ksm_thread_sleep_millisecs = msecs; wake_up_interruptible(&ksm_iter_wait); return count; } KSM_ATTR(sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_thread_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int nr_pages; int err; if (ksm_advisor != KSM_ADVISOR_NONE) return -EINVAL; err = kstrtouint(buf, 10, &nr_pages); if (err) return -EINVAL; ksm_thread_pages_to_scan = nr_pages; return count; } KSM_ATTR(pages_to_scan); static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_run); } static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int flags; int err; err = kstrtouint(buf, 10, &flags); if (err) return -EINVAL; if (flags > KSM_RUN_UNMERGE) return -EINVAL; /* * KSM_RUN_MERGE sets ksmd running, and 0 stops it running. * KSM_RUN_UNMERGE stops it running and unmerges all rmap_items, * breaking COW to free the pages_shared (but leaves mm_slots * on the list for when ksmd may be set running again). */ mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_run != flags) { ksm_run = flags; if (flags & KSM_RUN_UNMERGE) { set_current_oom_origin(); err = unmerge_and_remove_all_rmap_items(); clear_current_oom_origin(); if (err) { ksm_run = KSM_RUN_STOP; count = err; } } } mutex_unlock(&ksm_thread_mutex); if (flags & KSM_RUN_MERGE) wake_up_interruptible(&ksm_thread_wait); return count; } KSM_ATTR(run); #ifdef CONFIG_NUMA static ssize_t merge_across_nodes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_merge_across_nodes); } static ssize_t merge_across_nodes_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long knob; err = kstrtoul(buf, 10, &knob); if (err) return err; if (knob > 1) return -EINVAL; mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_merge_across_nodes != knob) { if (ksm_pages_shared || remove_all_stable_nodes()) err = -EBUSY; else if (root_stable_tree == one_stable_tree) { struct rb_root *buf; /* * This is the first time that we switch away from the * default of merging across nodes: must now allocate * a buffer to hold as many roots as may be needed. * Allocate stable and unstable together: * MAXSMP NODES_SHIFT 10 will use 16kB. */ buf = kcalloc(nr_node_ids + nr_node_ids, sizeof(*buf), GFP_KERNEL); /* Let us assume that RB_ROOT is NULL is zero */ if (!buf) err = -ENOMEM; else { root_stable_tree = buf; root_unstable_tree = buf + nr_node_ids; /* Stable tree is empty but not the unstable */ root_unstable_tree[0] = one_unstable_tree[0]; } } if (!err) { ksm_merge_across_nodes = knob; ksm_nr_node_ids = knob ? 1 : nr_node_ids; } } mutex_unlock(&ksm_thread_mutex); return err ? err : count; } KSM_ATTR(merge_across_nodes); #endif static ssize_t use_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_use_zero_pages); } static ssize_t use_zero_pages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; bool value; err = kstrtobool(buf, &value); if (err) return -EINVAL; ksm_use_zero_pages = value; return count; } KSM_ATTR(use_zero_pages); static ssize_t max_page_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_max_page_sharing); } static ssize_t max_page_sharing_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; int knob; err = kstrtoint(buf, 10, &knob); if (err) return err; /* * When a KSM page is created it is shared by 2 mappings. This * being a signed comparison, it implicitly verifies it's not * negative. */ if (knob < 2) return -EINVAL; if (READ_ONCE(ksm_max_page_sharing) == knob) return count; mutex_lock(&ksm_thread_mutex); wait_while_offlining(); if (ksm_max_page_sharing != knob) { if (ksm_pages_shared || remove_all_stable_nodes()) err = -EBUSY; else ksm_max_page_sharing = knob; } mutex_unlock(&ksm_thread_mutex); return err ? err : count; } KSM_ATTR(max_page_sharing); static ssize_t pages_scanned_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_scanned); } KSM_ATTR_RO(pages_scanned); static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_shared); } KSM_ATTR_RO(pages_shared); static ssize_t pages_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_sharing); } KSM_ATTR_RO(pages_sharing); static ssize_t pages_unshared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_unshared); } KSM_ATTR_RO(pages_unshared); static ssize_t pages_volatile_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { long ksm_pages_volatile; ksm_pages_volatile = ksm_rmap_items - ksm_pages_shared - ksm_pages_sharing - ksm_pages_unshared; /* * It was not worth any locking to calculate that statistic, * but it might therefore sometimes be negative: conceal that. */ if (ksm_pages_volatile < 0) ksm_pages_volatile = 0; return sysfs_emit(buf, "%ld\n", ksm_pages_volatile); } KSM_ATTR_RO(pages_volatile); static ssize_t pages_skipped_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_pages_skipped); } KSM_ATTR_RO(pages_skipped); static ssize_t ksm_zero_pages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); } KSM_ATTR_RO(ksm_zero_pages); static ssize_t general_profit_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { long general_profit; general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - ksm_rmap_items * sizeof(struct ksm_rmap_item); return sysfs_emit(buf, "%ld\n", general_profit); } KSM_ATTR_RO(general_profit); static ssize_t stable_node_dups_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_stable_node_dups); } KSM_ATTR_RO(stable_node_dups); static ssize_t stable_node_chains_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_stable_node_chains); } KSM_ATTR_RO(stable_node_chains); static ssize_t stable_node_chains_prune_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_stable_node_chains_prune_millisecs); } static ssize_t stable_node_chains_prune_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; ksm_stable_node_chains_prune_millisecs = msecs; return count; } KSM_ATTR(stable_node_chains_prune_millisecs); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_scan.seqnr); } KSM_ATTR_RO(full_scans); static ssize_t smart_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_smart_scan); } static ssize_t smart_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; bool value; err = kstrtobool(buf, &value); if (err) return -EINVAL; ksm_smart_scan = value; return count; } KSM_ATTR(smart_scan); static ssize_t advisor_mode_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (ksm_advisor == KSM_ADVISOR_NONE) output = "[none] scan-time"; else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) output = "none [scan-time]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t advisor_mode_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { enum ksm_advisor_type curr_advisor = ksm_advisor; if (sysfs_streq("scan-time", buf)) ksm_advisor = KSM_ADVISOR_SCAN_TIME; else if (sysfs_streq("none", buf)) ksm_advisor = KSM_ADVISOR_NONE; else return -EINVAL; /* Set advisor default values */ if (curr_advisor != ksm_advisor) set_advisor_defaults(); return count; } KSM_ATTR(advisor_mode); static ssize_t advisor_max_cpu_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", ksm_advisor_max_cpu); } static ssize_t advisor_max_cpu_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_max_cpu = value; return count; } KSM_ATTR(advisor_max_cpu); static ssize_t advisor_min_pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_min_pages_to_scan); } static ssize_t advisor_min_pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_min_pages_to_scan = value; return count; } KSM_ATTR(advisor_min_pages_to_scan); static ssize_t advisor_max_pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_max_pages_to_scan); } static ssize_t advisor_max_pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; ksm_advisor_max_pages_to_scan = value; return count; } KSM_ATTR(advisor_max_pages_to_scan); static ssize_t advisor_target_scan_time_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", ksm_advisor_target_scan_time); } static ssize_t advisor_target_scan_time_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long value; err = kstrtoul(buf, 10, &value); if (err) return -EINVAL; if (value < 1) return -EINVAL; ksm_advisor_target_scan_time = value; return count; } KSM_ATTR(advisor_target_scan_time); static struct attribute *ksm_attrs[] = { &sleep_millisecs_attr.attr, &pages_to_scan_attr.attr, &run_attr.attr, &pages_scanned_attr.attr, &pages_shared_attr.attr, &pages_sharing_attr.attr, &pages_unshared_attr.attr, &pages_volatile_attr.attr, &pages_skipped_attr.attr, &ksm_zero_pages_attr.attr, &full_scans_attr.attr, #ifdef CONFIG_NUMA &merge_across_nodes_attr.attr, #endif &max_page_sharing_attr.attr, &stable_node_chains_attr.attr, &stable_node_dups_attr.attr, &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, &general_profit_attr.attr, &smart_scan_attr.attr, &advisor_mode_attr.attr, &advisor_max_cpu_attr.attr, &advisor_min_pages_to_scan_attr.attr, &advisor_max_pages_to_scan_attr.attr, &advisor_target_scan_time_attr.attr, NULL, }; static const struct attribute_group ksm_attr_group = { .attrs = ksm_attrs, .name = "ksm", }; #endif /* CONFIG_SYSFS */ static int __init ksm_init(void) { struct task_struct *ksm_thread; int err; /* The correct value depends on page size and endianness */ zero_checksum = calc_checksum(ZERO_PAGE(0)); /* Default to false for backwards compatibility */ ksm_use_zero_pages = false; err = ksm_slab_init(); if (err) goto out; ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd"); if (IS_ERR(ksm_thread)) { pr_err("ksm: creating kthread failed\n"); err = PTR_ERR(ksm_thread); goto out_free; } #ifdef CONFIG_SYSFS err = sysfs_create_group(mm_kobj, &ksm_attr_group); if (err) { pr_err("ksm: register sysfs failed\n"); kthread_stop(ksm_thread); goto out_free; } #else ksm_run = KSM_RUN_MERGE; /* no way for user to start it */ #endif /* CONFIG_SYSFS */ #ifdef CONFIG_MEMORY_HOTREMOVE /* There is no significance to this priority 100 */ hotplug_memory_notifier(ksm_memory_callback, KSM_CALLBACK_PRI); #endif return 0; out_free: ksm_slab_free(); out: return err; } subsys_initcall(ksm_init); |
| 5 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 IP device support routines. * * Derived from the 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: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * Alexey Kuznetsov: pa_* fields are replaced with ifaddr * lists. * Cyrus Durgin: updated for kmod * Matthias Andree: in devinet_ioctl, compare label and * address (4.4BSD alias style support), * fall back to comparing just the label * if no match found. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/kmod.h> #include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/addrconf.h> #define IPV6ONLY_FLAGS \ (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; static struct ipv4_devconf ipv4_devconf_dflt = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; #define IPV4_DEVCONF_DFLT(net, attr) \ IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr) static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFA_PROTO] = { .type = NLA_U8 }, }; struct inet_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; }; #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = __ipv4_addr_hash(addr, net_hash_mix(net)); return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); ASSERT_RTNL(); hlist_add_head_rcu(&ifa->addr_lst, &net->ipv4.inet_addr_lst[hash]); } static void inet_hash_remove(struct in_ifaddr *ifa) { ASSERT_RTNL(); hlist_del_init_rcu(&ifa->addr_lst); } /** * __ip_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @devref: if true, take a reference on the found device * * If a caller uses devref=false, it should be protected by RCU, or RTNL */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); ifa = inet_lookup_ifaddr_rcu(net, addr); if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; /* Fallback to FIB local table so that communication * over loopback subnets work. */ local = fib_get_table(net, RT_TABLE_LOCAL); if (local && !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); } else { result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL(__ip_dev_find); /* called under RCU lock */ struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) { u32 hash = inet_addr_hash(net, addr); struct in_ifaddr *ifa; hlist_for_each_entry_rcu(ifa, &net->ipv4.inet_addr_lst[hash], addr_lst) if (ifa->ifa_local == addr) return ifa; return NULL; } static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else static int devinet_sysctl_register(struct in_device *idev) { return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { } #endif /* Locks all the inet devices. */ static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { struct in_ifaddr *ifa; ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); if (!ifa) return NULL; in_dev_hold(in_dev); ifa->ifa_dev = in_dev; INIT_HLIST_NODE(&ifa->addr_lst); return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); in_dev_put(ifa->ifa_dev); kfree(ifa); } static void inet_free_ifa(struct in_ifaddr *ifa) { /* Our reference to ifa->ifa_dev must be freed ASAP * to release the reference to the netdev the same way. * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() */ call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); } static void in_dev_free_rcu(struct rcu_head *head) { struct in_device *idev = container_of(head, struct in_device, rcu_head); kfree(rcu_dereference_protected(idev->mc_hash, 1)); kfree(idev); } void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; int err = -ENOMEM; ASSERT_RTNL(); in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL); if (!in_dev) goto out; memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); if (dev != blackhole_netdev) { err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; } ip_mc_init_dev(in_dev); if (dev->flags & IFF_UP) ip_mc_up(in_dev); } /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; goto out; } static void inetdev_destroy(struct in_device *in_dev) { struct net_device *dev; struct in_ifaddr *ifa; ASSERT_RTNL(); dev = in_dev->dev; in_dev->dead = 1; ip_mc_destroy_dev(in_dev); while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); in_dev_put(in_dev); } static int __init inet_blackhole_dev_init(void) { int err = 0; rtnl_lock(); if (!inetdev_init(blackhole_netdev)) err = -ENOMEM; rtnl_unlock(); return err; } late_initcall(inet_blackhole_dev_init); int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { const struct in_ifaddr *ifa; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } } rcu_read_unlock(); return 0; } static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); last_prim = ifap; if (in_dev->dead) goto no_promotions; /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next; while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) { ifap1 = &ifa->ifa_next; prev_prom = ifa; continue; } if (!do_promote) { inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); } else { promote = ifa; break; } } } /* On promotion all secondaries from subnet are changing * the primary IP, we must remove all their routes silently * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); } no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; inet_hash_remove(ifa1); /* 3. Announce address deletion */ /* Send message first, then call notifier. At first sight, FIB update triggered by notifier will refer to already deleted ifaddr, that could confuse netlink listeners. It is not true: look, gated sees that route deleted and if it still thinks that ifaddr is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { struct in_ifaddr *next_sec; next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { struct in_ifaddr *last_sec; rcu_assign_pointer(prev_prom->ifa_next, next_sec); last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = next_sec; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; fib_add_ifaddr(ifa); } } if (destroy) inet_free_ifa(ifa1); } static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid, struct netlink_ext_ack *extack) { struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; struct net *net = dev_net(in_dev->dev); struct in_validator_info ivi; struct in_ifaddr *ifa1; int ret; ASSERT_RTNL(); ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; /* Don't set IPv6 only flags to IPv4 addresses */ ifa->ifa_flags &= ~IPV6ONLY_FLAGS; ifap = &in_dev->ifa_list; ifa1 = rtnl_dereference(*ifap); while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) { if (ifa1->ifa_local == ifa->ifa_local) { inet_free_ifa(ifa); return -EEXIST; } if (ifa1->ifa_scope != ifa->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid scope value"); inet_free_ifa(ifa); return -EINVAL; } ifa->ifa_flags |= IFA_F_SECONDARY; } ifap = &ifa1->ifa_next; ifa1 = rtnl_dereference(*ifap); } /* Allow any devices that wish to register ifaddr validtors to weigh * in now, before changes are committed. The rntl lock is serializing * access here, so the state should not change between a validator call * and a final notify on commit. This isn't invoked on promotion under * the assumption that validators are checking the address itself, and * not the flags. */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; ivi.extack = extack; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); if (ret) { inet_free_ifa(ifa); return ret; } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) ifap = last_primary; rcu_assign_pointer(ifa->ifa_next, *ifap); rcu_assign_pointer(*ifap, ifa); inet_hash_insert(dev_net(in_dev->dev), ifa); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; } static int inet_insert_ifa(struct in_ifaddr *ifa) { if (!ifa->ifa_local) { inet_free_ifa(ifa); return 0; } return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); } /* Caller must hold RCU or RTNL : * We dont take a reference on found in_device */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { struct in_ifaddr *ifa; ASSERT_RTNL(); in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; } return NULL; } static int ip_mc_autojoin_config(struct net *net, bool join, const struct in_ifaddr *ifa) { #if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL_NET(net); lock_sock(sk); if (join) ret = ip_mc_join_group(sk, &mreq); else ret = ip_mc_leave_group(sk, &mreq); release_sock(sk); return ret; #else return -EOPNOTSUPP; #endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; struct in_ifaddr *ifa; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) goto out; ifm = nlmsg_data(nlh); rtnl_net_lock(net); in_dev = inetdev_by_index(net, ifm->ifa_index); if (!in_dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); err = -ENODEV; goto unlock; } for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) continue; if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; if (ipv4_is_multicast(ifa->ifa_address)) ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); goto unlock; } NL_SET_ERR_MSG(extack, "ipv4: Address not found"); err = -EADDRNOTAVAIL; unlock: rtnl_net_unlock(net); out: return err; } static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; struct hlist_node *n; struct net *net; int i; net = container_of(to_delayed_work(work), struct net, ipv4.addr_chk_work); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); for (i = 0; i < IN4_ADDR_HSIZE; i++) { struct hlist_head *head = &net->ipv4.inet_addr_lst[i]; bool change_needed = false; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, head, addr_lst) { unsigned long age, tstamp; u32 preferred_lft; u32 valid_lft; u32 flags; flags = READ_ONCE(ifa->ifa_flags); if (flags & IFA_F_PERMANENT) continue; preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); valid_lft = READ_ONCE(ifa->ifa_valid_lft); tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (valid_lft != INFINITY_LIFE_TIME && age >= valid_lft) { change_needed = true; } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; } else if (age >= preferred_lft) { if (time_before(tstamp + valid_lft * HZ, next)) next = tstamp + valid_lft * HZ; if (!(flags & IFA_F_DEPRECATED)) change_needed = true; } else if (time_before(tstamp + preferred_lft * HZ, next)) { next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); if (!change_needed) continue; rtnl_net_lock(net); hlist_for_each_entry_safe(ifa, n, head, addr_lst) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) continue; /* We try to batch several events at once. */ age = (now - ifa->ifa_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { struct in_ifaddr __rcu **ifap; struct in_ifaddr *tmp; ifap = &ifa->ifa_dev->ifa_list; tmp = rtnl_net_dereference(net, *ifap); while (tmp) { if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } ifap = &tmp->ifa_next; tmp = rtnl_net_dereference(net, *ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_preferred_lft && !(ifa->ifa_flags & IFA_F_DEPRECATED)) { ifa->ifa_flags |= IFA_F_DEPRECATED; rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } rtnl_net_unlock(net); } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; now = jiffies; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; u32 flags; flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) WRITE_ONCE(ifa->ifa_valid_lft, timeout); else flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) flags |= IFA_F_DEPRECATED; WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } WRITE_ONCE(ifa->ifa_flags, flags); WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } static int inet_validate_rtm(struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack, __u32 *valid_lft, __u32 *prefered_lft) { struct ifaddrmsg *ifm = nlmsg_data(nlh); int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; if (ifm->ifa_prefixlen > 32) { NL_SET_ERR_MSG(extack, "ipv4: Invalid prefix length"); return -EINVAL; } if (!tb[IFA_LOCAL]) { NL_SET_ERR_MSG(extack, "ipv4: Local address is not supplied"); return -EINVAL; } if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { NL_SET_ERR_MSG(extack, "ipv4: address lifetime invalid"); return -EINVAL; } *valid_lft = ci->ifa_valid; *prefered_lft = ci->ifa_prefered; } return 0; } static struct in_ifaddr *inet_rtm_to_ifa(struct net *net, struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrmsg *ifm = nlmsg_data(nlh); struct in_device *in_dev; struct net_device *dev; struct in_ifaddr *ifa; int err; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; if (!dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); goto errout; } in_dev = __in_dev_get_rtnl_net(dev); err = -ENOBUFS; if (!in_dev) goto errout; ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. */ goto errout; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (tb[IFA_RT_PRIORITY]) ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); if (tb[IFA_PROTO]) ifa->ifa_proto = nla_get_u8(tb[IFA_PROTO]); return ifa; errout: return ERR_PTR(err); } static struct in_ifaddr *find_matching_ifa(struct net *net, struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1; in_dev_for_each_ifa_rtnl_net(net, ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) return ifa1; } return NULL; } static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { __u32 prefered_lft = INFINITY_LIFE_TIME; __u32 valid_lft = INFINITY_LIFE_TIME; struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa_existing; struct nlattr *tb[IFA_MAX + 1]; struct in_ifaddr *ifa; int ret; ret = inet_validate_rtm(nlh, tb, extack, &valid_lft, &prefered_lft); if (ret < 0) return ret; if (!nla_get_in_addr(tb[IFA_LOCAL])) return 0; rtnl_net_lock(net); ifa = inet_rtm_to_ifa(net, nlh, tb, extack); if (IS_ERR(ifa)) { ret = PTR_ERR(ifa); goto unlock; } ifa_existing = find_matching_ifa(net, ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { NL_SET_ERR_MSG(extack, "ipv4: Multicast auto join failed"); inet_free_ifa(ifa); goto unlock; } } ret = __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, extack); } else { u32 new_metric = ifa->ifa_rt_priority; u8 new_proto = ifa->ifa_proto; inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "ipv4: Address already assigned"); ret = -EEXIST; goto unlock; } ifa = ifa_existing; if (ifa->ifa_rt_priority != new_metric) { fib_modify_prefix_metric(ifa, new_metric); ifa->ifa_rt_priority = new_metric; } ifa->ifa_proto = new_proto; set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); } unlock: rtnl_net_unlock(net); return ret; } /* * Determine a default network mask, based on the IP address. */ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; else if (IN_CLASSE(haddr)) rc = 32; } return rc; } int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) { struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; int ret = -EFAULT; int tryaddrmatch = 0; ifr->ifr_name[IFNAMSIZ - 1] = 0; /* save original address for comparison */ memcpy(&sin_orig, sin, sizeof(*sin)); colon = strchr(ifr->ifr_name, ':'); if (colon) *colon = 0; dev_load(net, ifr->ifr_name); switch (cmd) { case SIOCGIFADDR: /* Get interface address */ case SIOCGIFBRDADDR: /* Get the broadcast address */ case SIOCGIFDSTADDR: /* Get the destination address */ case SIOCGIFNETMASK: /* Get the netmask for the interface */ /* Note that these ioctls will not sleep, so that we do not impose a lock. One day we will be forced to put shlock here (I mean SMP) */ tryaddrmatch = (sin_orig.sin_family == AF_INET); memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_INET; break; case SIOCSIFFLAGS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) goto out; break; default: ret = -EINVAL; goto out; } rtnl_net_lock(net); ret = -ENODEV; dev = __dev_get_by_name(net, ifr->ifr_name); if (!dev) goto done; if (colon) *colon = ':'; in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == ifa->ifa_local) { break; /* found */ } } } /* we didn't get a match, maybe the application is 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; } } ret = -EADDRNOTAVAIL; if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS) goto done; switch (cmd) { case SIOCGIFADDR: /* Get interface address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_local; break; case SIOCGIFBRDADDR: /* Get the broadcast address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_broadcast; break; case SIOCGIFDSTADDR: /* Get the destination address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_address; break; case SIOCGIFNETMASK: /* Get the netmask for the interface */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_mask; break; case SIOCSIFFLAGS: if (colon) { ret = -EADDRNOTAVAIL; if (!ifa) break; ret = 0; if (!(ifr->ifr_flags & IFF_UP)) inet_del_ifa(in_dev, ifap, 1); break; } /* NETDEV_UP/DOWN/CHANGE could touch a peer dev */ ASSERT_RTNL(); ret = dev_change_flags(dev, ifr->ifr_flags, NULL); break; case SIOCSIFADDR: /* Set interface address (and family) */ ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; if (!ifa) { ret = -ENOBUFS; if (!in_dev) break; ifa = inet_alloc_ifa(in_dev); if (!ifa) break; if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); } else { ret = 0; if (ifa->ifa_local == sin->sin_addr.s_addr) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; ifa->ifa_scope = 0; } ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr; if (!(dev->flags & IFF_POINTOPOINT)) { ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address); ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen); if ((dev->flags & IFF_BROADCAST) && ifa->ifa_prefixlen < 31) ifa->ifa_broadcast = ifa->ifa_address | ~ifa->ifa_mask; } else { ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; case SIOCSIFBRDADDR: /* Set the broadcast address */ ret = 0; if (ifa->ifa_broadcast != sin->sin_addr.s_addr) { inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = sin->sin_addr.s_addr; inet_insert_ifa(ifa); } break; case SIOCSIFDSTADDR: /* Set the destination address */ ret = 0; if (ifa->ifa_address == sin->sin_addr.s_addr) break; ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; ret = 0; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_address = sin->sin_addr.s_addr; inet_insert_ifa(ifa); break; case SIOCSIFNETMASK: /* Set the netmask for the interface */ /* * The mask we set must be legal. */ ret = -EINVAL; if (bad_mask(sin->sin_addr.s_addr, 0)) break; ret = 0; if (ifa->ifa_mask != sin->sin_addr.s_addr) { __be32 old_mask = ifa->ifa_mask; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_mask = sin->sin_addr.s_addr; ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask); /* See if current broadcast address matches * with current netmask, then recalculate * the broadcast address. Otherwise it's a * funny address, so don't touch it since * the user seems to know what (s)he's doing... */ if ((dev->flags & IFF_BROADCAST) && (ifa->ifa_prefixlen < 31) && (ifa->ifa_broadcast == (ifa->ifa_local|~old_mask))) { ifa->ifa_broadcast = (ifa->ifa_local | ~sin->sin_addr.s_addr); } inet_insert_ifa(ifa); } break; } done: rtnl_net_unlock(net); out: return ret; } int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; if (WARN_ON(size > sizeof(struct ifreq))) goto out; if (!in_dev) goto out; in_dev_for_each_ifa_rtnl_net(dev_net(dev), ifa, in_dev) { if (!buf) { done += size; continue; } if (len < size) break; memset(&ifr, 0, sizeof(struct ifreq)); strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = ifa->ifa_local; if (copy_to_user(buf + done, &ifr, size)) { done = -EFAULT; break; } len -= size; done += size; } out: return done; } static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; } return 0; } __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { const struct in_ifaddr *ifa; __be32 addr = 0; unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; struct net *net = dev_net(dev); int master_idx; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; break; } if (!addr) addr = ifa->ifa_local; } if (addr) goto out_unlock; no_in_dev: master_idx = l3mdev_master_ifindex_rcu(dev); /* For VRFs, the VRF device takes the place of the loopback device, * with addresses on it being preferred. Note in such cases the * loopback device will be among the devices that fail the master_idx * equality check in the loop below. */ if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } /* Not loopback addresses on loopback should be preferred in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } out_unlock: rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { unsigned char localnet_scope = RT_SCOPE_HOST; const struct in_ifaddr *ifa; __be32 addr = 0; int same = 0; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { unsigned char min_scope = min(ifa->ifa_scope, localnet_scope); if (!addr && (local == ifa->ifa_local || !local) && min_scope <= scope) { addr = ifa->ifa_local; if (same) break; } if (!same) { same = (!local || inet_ifa_match(local, ifa)) && (!dst || inet_ifa_match(dst, ifa)); if (same && addr) { if (local || !dst) break; /* Is the selected addr into dst subnet? */ if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ if (min_scope <= scope) { addr = ifa->ifa_local; break; } /* search for large dst subnet for addr */ same = 0; } } } return same ? addr : 0; } /* * Confirm that local IP address exists using wildcards: * - net: netns to check, cannot be NULL * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_confirm_addr); /* * Device notifier */ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_notifier); int register_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(register_inetaddr_validator_notifier); int unregister_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { struct in_ifaddr *ifa; int named = 0; in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (named++ == 0) goto skip; dot = strchr(old, ':'); if (!dot) { sprintf(old, ":%d", named); dot = old; } if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, dev->dev_addr, NULL); } } /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); if (IS_ERR(in_dev)) return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); } } else if (event == NETDEV_CHANGEMTU) { /* Re-enabling IP */ if (inetdev_valid_mtu(dev->mtu)) in_dev = inetdev_init(dev); } goto out; } switch (event) { case NETDEV_REGISTER: pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } ip_mc_up(in_dev); fallthrough; case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; fallthrough; case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); break; case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ fallthrough; case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; case NETDEV_CHANGENAME: /* Do not notify about label change, this event is * not interesting to applications using netlink. */ inetdev_changename(dev, in_dev); devinet_sysctl_unregister(in_dev); devinet_sysctl_register(in_dev); break; } out: return NOTIFY_DONE; } static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned long tstamp; u32 preferred, valid; u32 flags; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; flags = READ_ONCE(ifa->ifa_flags); /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits. * The 32bit value is given in IFA_FLAGS attribute. */ ifm->ifa_flags = (__u8)flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto nla_put_failure; tstamp = READ_ONCE(ifa->ifa_tstamp); if (!(flags & IFA_F_PERMANENT)) { preferred = READ_ONCE(ifa->ifa_preferred_lft); valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || nla_put_u32(skb, IFA_FLAGS, flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct inet_fill_args *fillargs, struct net **tgt_net, struct sock *sk, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[IFA_MAX+1]; struct ifaddrmsg *ifm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request"); return -EINVAL; } fillargs->ifindex = ifm->ifa_index; if (fillargs->ifindex) { cb->answer_flags |= NLM_F_DUMP_FILTERED; fillargs->flags |= NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= IFA_MAX; ++i) { if (!tb[i]) continue; if (i == IFA_TARGET_NETNSID) { struct net *net; fillargs->netnsid = nla_get_s32(tb[i]); net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); if (IS_ERR(net)) { fillargs->netnsid = -1; NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id"); return PTR_ERR(net); } *tgt_net = net; } else { NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; int err; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (ip_idx < *s_ip_idx) { ip_idx++; continue; } err = inet_fill_ifaddr(skb, ifa, fillargs); if (err < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); ip_idx++; } err = 0; ip_idx = 0; done: *s_ip_idx = ip_idx; return err; } /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv4.dev_addr_genid) + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. */ if (!res) res = 0x80000000; return res; } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, .event = RTM_NEWADDR, .flags = NLM_F_MULTI, .netnsid = -1, }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; struct { unsigned long ifindex; int ip_idx; } *ctx = (void *)cb->ctx; struct in_device *in_dev; struct net_device *dev; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) goto done; if (fillargs.ifindex) { dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; goto done; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); goto done; } } cb->seq = inet_base_seq(tgt_net); for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); if (err < 0) goto done; } done: if (fillargs.netnsid >= 0) put_net(tgt_net); rcu_read_unlock(); return err; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { struct inet_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .event = event, .flags = 0, .netnsid = -1, }; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (!in_dev) return 0; return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; int i; if (!in_dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { [IFLA_INET_CONF] = { .type = NLA_NESTED }, }; static int inet_validate_link_af(const struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, inet_af_policy, extack); if (err < 0) return err; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { int cfgid = nla_type(a); if (nla_len(a) < 4) return -EINVAL; if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) return -EINVAL; } } return 0; } static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; if (!in_dev) return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); } return 0; } static int inet_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_RP_FILTER) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_BC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, const struct ipv4_devconf *devconf, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF_RO(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; const struct ipv4_devconf *devconf; struct in_device *in_dev = NULL; struct net_device *dev = NULL; struct sk_buff *skb; int ifindex; int err; err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err) return err; if (!tb[NETCONFA_IFINDEX]) return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv4.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv4.devconf_dflt; break; default: err = -ENODEV; dev = dev_get_by_index(net, ifindex); if (dev) in_dev = in_dev_get(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: if (in_dev) in_dev_put(in_dev); dev_put(dev); return err; } static int inet_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; unsigned int all_default; } *ctx = (void *)cb->ctx; const struct in_device *in_dev; struct net_device *dev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = inet_netconf_fill_devconf(skb, dev->ifindex, &in_dev->cnf, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; } if (ctx->all_default == 0) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } if (ctx->all_default == 1) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } done: rcu_read_unlock(); return err; } #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; } rcu_read_unlock(); } /* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; int on = IPV4_DEVCONF_ALL(net, FORWARDING); IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) dev_disable_lro(dev); in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } } } static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) { if (cnf == net->ipv4.devconf_dflt) return NETCONFA_IFINDEX_DEFAULT; else if (cnf == net->ipv4.devconf_all) return NETCONFA_IFINDEX_ALL; else { struct in_device *idev = container_of(cnf, struct in_device, cnf); return idev->dev->ifindex; } } static int devinet_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; int ifindex; set_bit(i, cnf->state); if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && new_value != old_value) rt_cache_flush(net); if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_RP_FILTER, ifindex, cnf); } if (i == IPV4_DEVCONF_PROXY_ARP - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, ifindex, cnf); } if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } return ret; } static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct net *net = ctl->extra2; int ret; if (write && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { if (!rtnl_net_trylock(net)) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; return restart_syscall(); } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); } rtnl_net_unlock(net); rt_cache_flush(net); } else inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } return ret; } static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) rt_cache_flush(net); return ret; } #define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \ { \ .procname = name, \ .data = ipv4_devconf.data + \ IPV4_DEVCONF_ ## attr - 1, \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ .extra1 = &ipv4_devconf, \ } #define DEVINET_SYSCTL_RW_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc) #define DEVINET_SYSCTL_RO_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc) #define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) #define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \ DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"), DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"), DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"), DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"), DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"), DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"), DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL, "igmpv2_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL, "igmpv3_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN, "ignore_routes_with_linkdown"), DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, "drop_gratuitous_arp"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, "route_localnet"), DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST, "drop_unicast_in_l2_multicast"), }, }; static int __devinet_sysctl_register(struct net *net, char *dev_name, int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL_ACCOUNT); if (!t) goto out; for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; } snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) goto free; p->sysctl = t; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(t); out: return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; if (t) { cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int devinet_sysctl_register(struct in_device *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; } static void devinet_sysctl_unregister(struct in_device *idev) { struct net *net = dev_net(idev->dev); __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } static struct ctl_table ctl_forward_entry[] = { { .procname = "ip_forward", .data = &ipv4_devconf.data[ IPV4_DEVCONF_FORWARDING - 1], .maxlen = sizeof(int), .mode = 0644, .proc_handler = devinet_sysctl_forward, .extra1 = &ipv4_devconf, .extra2 = &init_net, }, }; #endif static __net_init int devinet_init_net(struct net *net) { #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; struct ctl_table *tbl; #endif struct ipv4_devconf *all, *dflt; int err; int i; err = -ENOMEM; net->ipv4.inet_addr_lst = kmalloc_array(IN4_ADDR_HSIZE, sizeof(struct hlist_head), GFP_KERNEL); if (!net->ipv4.inet_addr_lst) goto err_alloc_hash; all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; tbl[0].extra1 = all; tbl[0].extra2 = net; #endif if (!net_eq(net, &init_net)) { switch (net_inherit_devconf()) { case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 0: case 1: /* copy from init_net */ memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 2: /* use compiled values */ break; } } #ifdef CONFIG_SYSCTL err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; err = __devinet_sysctl_register(net, "default", NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; err = -ENOMEM; forw_hdr = register_net_sysctl_sz(net, "net/ipv4", tbl, ARRAY_SIZE(ctl_forward_entry)); if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif for (i = 0; i < IN4_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&net->ipv4.inet_addr_lst[i]); INIT_DEFERRABLE_WORK(&net->ipv4.addr_chk_work, check_lifetime); net->ipv4.devconf_all = all; net->ipv4.devconf_dflt = dflt; return 0; #ifdef CONFIG_SYSCTL err_reg_ctl: __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(tbl); err_alloc_ctl: #endif kfree(dflt); err_alloc_dflt: kfree(all); err_alloc_all: kfree(net->ipv4.inet_addr_lst); err_alloc_hash: return err; } static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; #endif cancel_delayed_work_sync(&net->ipv4.addr_chk_work); #ifdef CONFIG_SYSCTL tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __devinet_sysctl_unregister(net, net->ipv4.devconf_all, NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); kfree(net->ipv4.devconf_all); kfree(net->ipv4.inet_addr_lst); } static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, .validate_link_af = inet_validate_link_af, .set_link_af = inet_set_link_af, }; static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWADDR, .doit = inet_rtm_newaddr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELADDR, .doit = inet_rtm_deladdr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETADDR, .dumpit = inet_dump_ifaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); register_netdevice_notifier(&ip_netdev_notifier); if (rtnl_af_register(&inet_af_ops)) panic("Unable to register inet_af_ops\n"); rtnl_register_many(devinet_rtnl_msg_handlers); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Generic netlink support functions to configure an SMC-R PNET table * * Copyright IBM Corp. 2016 * * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> */ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc_pnet.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_core.h" static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [SMC_PNETID_IBNAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX - 1 }, [SMC_PNETID_IBPORT] = { .type = NLA_U8 } }; static struct genl_family smc_pnet_nl_family; enum smc_pnet_nametype { SMC_PNET_ETH = 1, SMC_PNET_IB = 2, }; /* pnet entry stored in pnet table */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNETID_LEN + 1]; enum smc_pnet_nametype type; union { struct { char eth_name[IFNAMSIZ + 1]; struct net_device *ndev; netdevice_tracker dev_tracker; }; struct { char ib_name[IB_DEVICE_NAME_MAX + 1]; u8 ib_port; }; }; }; /* Check if the pnetid is set */ bool smc_pnet_is_pnetid_set(u8 *pnetid) { if (pnetid[0] == 0 || pnetid[0] == _S) return false; return true; } /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { if ((pnetid1[i] == 0 || pnetid1[i] == _S) && (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; } return true; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct smc_ib_device *ibdev; struct smcd_dev *smcd; struct smc_net *sn; int rc = -ENOENT; int ibport; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* remove table entry */ mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); } kfree(pnetelem); rc = 0; } } mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) return rc; /* remove ib devices */ mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && (!pnet_name || smc_pnet_match(pnet_name, ibdev->pnetid[ibport]))) { pr_warn_ratelimited("smc: ib device %s ibport " "%d erased user defined " "pnetid %.16s\n", ibdev->ibdev->name, ibport + 1, ibdev->pnetid[ibport]); memset(ibdev->pnetid[ibport], 0, SMC_MAX_PNETID_LEN); ibdev->pnetid_by_user[ibport] = false; rc = 0; } } } mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->pnetid_by_user && (!pnet_name || smc_pnet_match(pnet_name, smcd->pnetid))) { pr_warn_ratelimited("smc: smcd device %s " "erased user defined pnetid " "%.16s\n", dev_name(smcd->ops->get_dev(smcd)), smcd->pnetid); memset(smcd->pnetid, 0, SMC_MAX_PNETID_LEN); smcd->pnetid_by_user = false; rc = 0; } } mutex_unlock(&smcd_dev_list.mutex); return rc; } /* Add the reference to a given network device to the pnet table. */ static int smc_pnet_add_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Remove the reference to a given network device from the pnet table. */ static int smc_pnet_remove_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Apply pnetid to ib device when no pnetid is set. */ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { bool applied = false; mutex_lock(&smc_ib_devices.mutex); if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } mutex_unlock(&smc_ib_devices.mutex); return applied; } /* Apply pnetid to smcd device when no pnetid is set. */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { bool applied = false; mutex_lock(&smcd_dev_list.mutex); if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } mutex_unlock(&smcd_dev_list.mutex); return applied; } /* The limit for pnetid is 16 characters. * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. * Lower case letters are converted to upper case. * Interior blanks should not be used. */ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) { char *bf = skip_spaces(pnet_name); size_t len = strlen(bf); char *end = bf + len; if (!len) return false; while (--end >= bf && isspace(*end)) ; if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) return false; *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; bf++; } *pnetid = '\0'; return true; } /* Find an infiniband device by a given name. The device might not exist. */ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || (ibdev->ibdev->dev.parent && !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, IB_DEVICE_NAME_MAX - 1))) { goto out; } } ibdev = NULL; out: mutex_unlock(&smc_ib_devices.mutex); return ibdev; } /* Find an smcd device by a given name. The device might not exist. */ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(smcd_dev->ops->get_dev(smcd_dev)), smcd_name, IB_DEVICE_NAME_MAX - 1)) goto out; } smcd_dev = NULL; out: mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, char *eth_name, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct net_device *ndev, *base_ndev; u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; bool new_netdev; int rc; /* check if (base) netdev already has a pnetid. If there is one, we do * not want to add a pnet table entry */ rc = -EEXIST; ndev = dev_get_by_name(net, eth_name); /* dev_hold() */ if (ndev) { base_ndev = pnet_find_base_ndev(ndev); if (!smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid)) goto out_put; } /* add a new netdev entry to the pnet table if there isn't one */ rc = -ENOMEM; new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) goto out_put; new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->eth_name, eth_name, IFNAMSIZ); rc = -EEXIST; new_netdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { new_netdev = false; break; } } if (new_netdev) { if (ndev) { new_pe->ndev = ndev; netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } if (ndev) pr_warn_ratelimited("smc: net device %s " "applied user defined pnetid %.16s\n", new_pe->eth_name, new_pe->pnet_name); return 0; out_put: dev_put(ndev); return rc; } static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, u8 ib_port, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct smc_ib_device *ib_dev; bool smcddev_applied = true; bool ibdev_applied = true; struct smcd_dev *smcd; struct device *dev; bool new_ibdev; /* try to apply the pnetid to active devices */ ib_dev = smc_pnet_find_ib(ib_name); if (ib_dev) { ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name); if (ibdev_applied) pr_warn_ratelimited("smc: ib device %s ibport %d " "applied user defined pnetid " "%.16s\n", ib_dev->ibdev->name, ib_port, ib_dev->pnetid[ib_port - 1]); } smcd = smc_pnet_find_smcd(ib_name); if (smcd) { smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name); if (smcddev_applied) { dev = smcd->ops->get_dev(smcd); pr_warn_ratelimited("smc: smcd device %s " "applied user defined pnetid " "%.16s\n", dev_name(dev), smcd->pnetid); } } /* Apply fails when a device has a hardware-defined pnetid set, do not * add a pnet table entry in that case. */ if (!ibdev_applied || !smcddev_applied) return -EEXIST; /* add a new ib entry to the pnet table if there isn't one */ new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) return -ENOMEM; new_pe->type = SMC_PNET_IB; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX); new_pe->ib_port = ib_port; new_ibdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { new_ibdev = false; break; } } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct net *net, struct nlattr *tb[]) { char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct smc_pnettable *pnettable; bool new_netdev = false; bool new_ibdev = false; struct smc_net *sn; u8 ibport = 1; char *string; int rc; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnet_name)) goto error; if (tb[SMC_PNETID_ETHNAME]) { string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); rc = smc_pnet_add_eth(pnettable, net, string, pnet_name); if (!rc) new_netdev = true; else if (rc != -EEXIST) goto error; } /* if this is not the initial namespace, stop here */ if (net != &init_net) return new_netdev ? 0 : -EEXIST; rc = -EINVAL; if (tb[SMC_PNETID_IBNAME]) { string = (char *)nla_data(tb[SMC_PNETID_IBNAME]); string = strim(string); if (tb[SMC_PNETID_IBPORT]) { ibport = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (ibport < 1 || ibport > SMC_MAX_PORTS) goto error; } rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name); if (!rc) new_ibdev = true; else if (rc != -EEXIST) goto error; } return (new_netdev || new_ibdev) ? 0 : -EEXIST; error: return rc; } /* Convert an smc_pnetentry to a netlink attribute sequence */ static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) { if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name)) return -1; if (pnetelem->type == SMC_PNET_ETH) { if (nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->eth_name)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a")) return -1; } if (pnetelem->type == SMC_PNET_IB) { if (nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->ib_name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") || nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff)) return -1; } return 0; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); return smc_pnet_enter(net, info->attrs); } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid(net, (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } static int smc_pnet_dump_start(struct netlink_callback *cb) { cb->args[0] = 0; return 0; } static int smc_pnet_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, struct smc_pnetentry *pnetelem) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, flags, SMC_PNETID_GET); if (!hdr) return -ENOMEM; if (smc_pnet_set_nla(skb, pnetelem) < 0) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid, int start_idx) { struct smc_pnettable *pnettable; struct smc_pnetentry *pnetelem; struct smc_net *sn; int idx = 0; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* dump pnettable entries */ mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; if (idx++ < start_idx) continue; /* if this is not the initial namespace, dump only netdev */ if (net != &init_net && pnetelem->type != SMC_PNET_ETH) continue; if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } mutex_unlock(&pnettable->lock); return idx; } static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx; idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NULL, cb->args[0]); cb->args[0] = idx; return skb->len; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct sk_buff *msg; void *hdr; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq, nla_data(info->attrs[SMC_PNETID_NAME]), 0); /* finish multi part message and send it */ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, NLM_F_MULTI); if (!hdr) { nlmsg_free(msg); return -EMSGSIZE; } return genlmsg_reply(msg, info); } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); smc_pnet_remove_by_pnetid(net, NULL); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops), .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe; bool rc = false; read_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { rc = true; goto unlock; } } unlock: read_unlock(&sn->pnetids_ndev.lock); return rc; } static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pi; pe = kzalloc(sizeof(*pe), GFP_KERNEL); if (!pe) return -ENOMEM; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; } } refcount_set(&pe->refcnt, 1); memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); list_add_tail(&pe->list, &sn->pnetids_ndev.list); unlock: write_unlock(&sn->pnetids_ndev.lock); return 0; } static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pe2; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { if (refcount_dec_and_test(&pe->refcnt)) { list_del(&pe->list); kfree(pe); } break; } } write_unlock(&sn->pnetids_ndev.lock); } static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, u8 *ndev_pnetid) { struct net_device *base_dev; base_dev = __pnet_find_base_ndev(dev); if (base_dev->flags & IFF_UP && !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, ndev_pnetid)) { /* add to PNETIDs list */ smc_pnet_add_pnetid(net, ndev_pnetid); } } /* create initial list of netdevice pnetids */ static void smc_pnet_create_pnetids_list(struct net *net) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; /* Newly created netns do not have devices. * Do not even acquire rtnl. */ if (list_empty(&net->dev_base_head)) return; /* Note: This might not be needed, because smc_pnet_netdev_event() * is also calling smc_pnet_add_base_pnetid() when handling * NETDEV_UP event. */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); rtnl_unlock(); } /* clean up list of netdevice pnetids */ static void smc_pnet_destroy_pnetids_list(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *temp_pe; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { list_del(&pe->list); kfree(pe); } write_unlock(&sn->pnetids_ndev.lock); } static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(event_dev); u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_UP: smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); return NOTIFY_OK; case NETDEV_DOWN: event_dev = __pnet_find_base_ndev(event_dev); if (!smc_pnetid_by_dev_port(event_dev->dev.parent, event_dev->dev_port, ndev_pnetid)) { /* remove from PNETIDs list */ smc_pnet_remove_pnetid(net, ndev_pnetid); } return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; /* init network namespace */ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); smc_pnet_create_pnetids_list(net); return 0; } int __init smc_pnet_init(void) { int rc; rc = genl_register_family(&smc_pnet_nl_family); if (rc) return rc; rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); return rc; } /* exit network namespace */ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) { unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; if (list_empty(lower)) break; lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } return ndev; } /* Determine one base device for stacked net devices. * If the lower device level contains more than one devices * (for instance with bonding slaves), just the first device * is used to reach a base device. */ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { rtnl_lock(); ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, u8 *pnetid) { struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_pnetentry *pnetelem; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, struct smc_init_info *ini) { if (!ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, NULL)) { ini->ib_dev = ibdev; ini->ib_port = i; return 0; } if (ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, NULL, &ini->smcrv2)) { ini->smcrv2.ib_dev_v2 = ibdev; ini->smcrv2.ib_port_v2 = i; return 0; } return -ENODEV; } /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, struct smc_ib_device *known_dev, struct net *net) { struct smc_ib_device *ibdev; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev || !rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) goto out; } } } out: mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id, vlan_id and net namespace */ void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev) { struct net *net = lgr->net; _smc_pnet_find_roce_by_pnetid(lgr->pnet_id, ini, known_dev, net); } /* if handshake network device belongs to a roce device, return its * IB device and port */ static void smc_pnet_find_rdma_dev(struct net_device *netdev, struct smc_init_info *ini) { struct net *net = dev_net(netdev); struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; /* check rdma net namespace */ if (!rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) break; } } } mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. * If nothing found, check pnetid table. * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net *net; ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { smc_pnet_find_rdma_dev(ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); } static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smcd_dev *ismdev; ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && (!ini->ism_peer_gid[0].gid || !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; } } mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: * determine ib_device and port belonging to used internal TCP socket * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_roce_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); ini->ism_dev[0] = NULL; if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_ism_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } /* Lookup and apply a pnet table entry to the given ib device. */ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) { char *ib_name = smcibdev->ibdev->name; struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && tmp_pe->ib_port == ib_port) { smc_pnet_apply_ib(smcibdev, ib_port, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } /* Lookup and apply a pnet table entry to the given smcd device. */ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) { const char *ib_name = dev_name(smcddev->ops->get_dev(smcddev)); struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { smc_pnet_apply_smcd(smcddev, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* isotp.c - ISO 15765-2 CAN transport protocol for protocol family CAN * * This implementation does not provide ISO-TP specific return values to the * userspace. * * - RX path timeout of data reception leads to -ETIMEDOUT * - RX path SN mismatch leads to -EILSEQ * - RX path data reception with wrong padding leads to -EBADMSG * - TX path flowcontrol reception timeout leads to -ECOMM * - TX path flowcontrol reception overflow leads to -EMSGSIZE * - TX path flowcontrol reception with wrong layout/padding leads to -EBADMSG * - when a transfer (tx) is on the run the next write() blocks until it's done * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent * - as we have static buffers the check whether the PDU fits into the buffer * is done at FF reception time (no support for sending 'wait frames') * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. */ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/wait.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/isotp.h> #include <linux/slab.h> #include <net/sock.h> #include <net/net_namespace.h> MODULE_DESCRIPTION("PF_CAN ISO 15765-2 transport protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); MODULE_ALIAS("can-proto-6"); #define ISOTP_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp) #define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) /* Since ISO 15765-2:2016 the CAN isotp protocol supports more than 4095 * byte per ISO PDU as the FF_DL can take full 32 bit values (4 Gbyte). * We would need some good concept to handle this between user space and * kernel space. For now set the static buffer to something about 8 kbyte * to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 /* maximum PDU size before ISO 15765-2:2016 extension was 4095 */ #define MAX_12BIT_PDU_SIZE 4095 /* limit the isotp pdu size from the optional module parameter to 1MByte */ #define MAX_PDU_SIZE (1025 * 1024U) static unsigned int max_pdu_size __read_mostly = DEFAULT_MAX_PDU_SIZE; module_param(max_pdu_size, uint, 0444); MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default " __stringify(DEFAULT_MAX_PDU_SIZE) ")"); /* N_PCI type values in bits 7-4 of N_PCI bytes */ #define N_PCI_SF 0x00 /* single frame */ #define N_PCI_FF 0x10 /* first frame */ #define N_PCI_CF 0x20 /* consecutive frame */ #define N_PCI_FC 0x30 /* flow control */ #define N_PCI_SZ 1 /* size of the PCI byte #1 */ #define SF_PCI_SZ4 1 /* size of SingleFrame PCI including 4 bit SF_DL */ #define SF_PCI_SZ8 2 /* size of SingleFrame PCI including 8 bit SF_DL */ #define FF_PCI_SZ12 2 /* size of FirstFrame PCI including 12 bit FF_DL */ #define FF_PCI_SZ32 6 /* size of FirstFrame PCI including 32 bit FF_DL */ #define FC_CONTENT_SZ 3 /* flow control content size in byte (FS/BS/STmin) */ #define ISOTP_CHECK_PADDING (CAN_ISOTP_CHK_PAD_LEN | CAN_ISOTP_CHK_PAD_DATA) #define ISOTP_ALL_BC_FLAGS (CAN_ISOTP_SF_BROADCAST | CAN_ISOTP_CF_BROADCAST) /* Flow Status given in FC frame */ #define ISOTP_FC_CTS 0 /* clear to send */ #define ISOTP_FC_WT 1 /* wait */ #define ISOTP_FC_OVFLW 2 /* overflow */ #define ISOTP_FC_TIMEOUT 1 /* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2 /* 2 secs */ enum { ISOTP_IDLE = 0, ISOTP_WAIT_FIRST_FC, ISOTP_WAIT_FC, ISOTP_WAIT_DATA, ISOTP_SENDING, ISOTP_SHUTDOWN, }; struct tpcon { u8 *buf; unsigned int buflen; unsigned int len; unsigned int idx; u32 state; u8 bs; u8 sn; u8 ll_dl; u8 sbuf[DEFAULT_MAX_PDU_SIZE]; }; struct isotp_sock { struct sock sk; int bound; int ifindex; canid_t txid; canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; struct hrtimer rxtimer, txtimer, txfrtimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; u32 frame_txtime; u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; spinlock_t rx_lock; /* protect single thread state machine */ }; static LIST_HEAD(isotp_notifier_list); static DEFINE_SPINLOCK(isotp_notifier_lock); static struct isotp_sock *isotp_busy_notifier; static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; } static u32 isotp_bc_flags(struct isotp_sock *so) { return so->opt.flags & ISOTP_ALL_BC_FLAGS; } static bool isotp_register_rxid(struct isotp_sock *so) { /* no broadcast modes => register rx_id for FC frame reception */ return (isotp_bc_flags(so) == 0); } static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, rxtimer); struct sock *sk = &so->sk; if (so->rx.state == ISOTP_WAIT_DATA) { /* we did not get new data frames in time */ /* report 'connection timed out' */ sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; } return HRTIMER_NORESTART; } static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) { struct net_device *dev; struct sk_buff *nskb; struct canfd_frame *ncf; struct isotp_sock *so = isotp_sk(sk); int can_send_ret; nskb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), gfp_any()); if (!nskb) return 1; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { kfree_skb(nskb); return 1; } can_skb_reserve(nskb); can_skb_prv(nskb)->ifindex = dev->ifindex; can_skb_prv(nskb)->skbcnt = 0; nskb->dev = dev; can_skb_set_owner(nskb, sk); ncf = (struct canfd_frame *)nskb->data; skb_put_zero(nskb, so->ll.mtu); /* create & send flow control reply */ ncf->can_id = so->txid; if (so->opt.flags & CAN_ISOTP_TX_PADDING) { memset(ncf->data, so->opt.txpad_content, CAN_MAX_DLEN); ncf->len = CAN_MAX_DLEN; } else { ncf->len = ae + FC_CONTENT_SZ; } ncf->data[ae] = N_PCI_FC | flowstatus; ncf->data[ae + 1] = so->rxfc.bs; ncf->data[ae + 2] = so->rxfc.stmin; if (ae) ncf->data[0] = so->opt.ext_address; ncf->flags = so->ll.tx_flags; can_send_ret = can_send(nskb, 1); if (can_send_ret) pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(can_send_ret)); dev_put(dev); /* reset blocksize counter */ so->rx.bs = 0; /* reset last CF frame rx timestamp for rx stmin enforcement */ so->lastrxcf_tstamp = ktime_set(0, 0); /* start rx timeout watchdog */ hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk) { struct sockaddr_can *addr = (struct sockaddr_can *)skb->cb; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can)); memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; if (sock_queue_rcv_skb(sk, skb) < 0) kfree_skb(skb); } static u8 padlen(u8 datalen) { static const u8 plen[] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */ 12, 12, 12, 12, /* 9 - 12 */ 16, 16, 16, 16, /* 13 - 16 */ 20, 20, 20, 20, /* 17 - 20 */ 24, 24, 24, 24, /* 21 - 24 */ 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */ 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */ 48, 48, 48, 48, 48, 48, 48, 48 /* 41 - 48 */ }; if (datalen > 48) return 64; return plen[datalen]; } /* check for length optimization and return 1/true when the check fails */ static int check_optimized(struct canfd_frame *cf, int start_index) { /* for CAN_DL <= 8 the start_index is equal to the CAN_DL as the * padding would start at this point. E.g. if the padding would * start at cf.data[7] cf->len has to be 7 to be optimal. * Note: The data[] index starts with zero. */ if (cf->len <= CAN_MAX_DLEN) return (cf->len != start_index); /* This relation is also valid in the non-linear DLC range, where * we need to take care of the minimal next possible CAN_DL. * The correct check would be (padlen(cf->len) != padlen(start_index)). * But as cf->len can only take discrete values from 12, .., 64 at this * point the padlen(cf->len) is always equal to cf->len. */ return (cf->len != padlen(start_index)); } /* check padding and return 1/true when the check fails */ static int check_pad(struct isotp_sock *so, struct canfd_frame *cf, int start_index, u8 content) { int i; /* no RX_PADDING value => check length of optimized frame length */ if (!(so->opt.flags & CAN_ISOTP_RX_PADDING)) { if (so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) return check_optimized(cf, start_index); /* no valid test against empty value => ignore frame */ return 1; } /* check datalength of correctly padded CAN frame */ if ((so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) && cf->len != padlen(cf->len)) return 1; /* check padding content */ if (so->opt.flags & CAN_ISOTP_CHK_PAD_DATA) { for (i = start_index; i < cf->len; i++) if (cf->data[i] != content) return 1; } return 0; } static void isotp_send_cframe(struct isotp_sock *so); static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) { struct sock *sk = &so->sk; if (so->tx.state != ISOTP_WAIT_FC && so->tx.state != ISOTP_WAIT_FIRST_FC) return 0; hrtimer_cancel(&so->txtimer); if ((cf->len < ae + FC_CONTENT_SZ) || ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return 1; } /* get static/dynamic communication params from first/every FC frame */ if (so->tx.state == ISOTP_WAIT_FIRST_FC || so->opt.flags & CAN_ISOTP_DYN_FC_PARMS) { so->txfc.bs = cf->data[ae + 1]; so->txfc.stmin = cf->data[ae + 2]; /* fix wrong STmin values according spec */ if (so->txfc.stmin > 0x7F && (so->txfc.stmin < 0xF1 || so->txfc.stmin > 0xF9)) so->txfc.stmin = 0x7F; so->tx_gap = ktime_set(0, 0); /* add transmission time for CAN frame N_As */ so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime); /* add waiting time for consecutive frames N_Cs */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_add_ns(so->tx_gap, so->force_tx_stmin); else if (so->txfc.stmin < 0x80) so->tx_gap = ktime_add_ns(so->tx_gap, so->txfc.stmin * 1000000); else so->tx_gap = ktime_add_ns(so->tx_gap, (so->txfc.stmin - 0xF0) * 100000); so->tx.state = ISOTP_WAIT_FC; } switch (cf->data[ae] & 0x0F) { case ISOTP_FC_CTS: so->tx.bs = 0; so->tx.state = ISOTP_SENDING; /* send CF frame and enable echo timeout handling */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); break; case ISOTP_FC_WT: /* start timer to wait for next FC frame */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); break; case ISOTP_FC_OVFLW: /* overflow on receiver side - report 'message too long' */ sk->sk_err = EMSGSIZE; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); fallthrough; default: /* stop this tx job */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); } return 0; } static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, struct sk_buff *skb, int len) { struct isotp_sock *so = isotp_sk(sk); struct sk_buff *nskb; hrtimer_cancel(&so->rxtimer); so->rx.state = ISOTP_IDLE; if (!len || len > cf->len - pcilen) return 1; if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, pcilen + len, so->opt.rxpad_content)) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 1; } nskb = alloc_skb(len, gfp_any()); if (!nskb) return 1; memcpy(skb_put(nskb, len), &cf->data[pcilen], len); nskb->tstamp = skb->tstamp; nskb->dev = skb->dev; isotp_rcv_skb(nskb, sk); return 0; } static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae) { struct isotp_sock *so = isotp_sk(sk); int i; int off; int ff_pci_sz; hrtimer_cancel(&so->rxtimer); so->rx.state = ISOTP_IDLE; /* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl = padlen(cf->len); /* the first frame has to use the entire frame up to LL_DL length */ if (cf->len != so->rx.ll_dl) return 1; /* get the FF_DL */ so->rx.len = (cf->data[ae] & 0x0F) << 8; so->rx.len += cf->data[ae + 1]; /* Check for FF_DL escape sequence supporting 32 bit PDU length */ if (so->rx.len) { ff_pci_sz = FF_PCI_SZ12; } else { /* FF_DL = 0 => get real length from next 4 bytes */ so->rx.len = cf->data[ae + 2] << 24; so->rx.len += cf->data[ae + 3] << 16; so->rx.len += cf->data[ae + 4] << 8; so->rx.len += cf->data[ae + 5]; ff_pci_sz = FF_PCI_SZ32; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->rx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; if (so->rx.len + ae + off + ff_pci_sz < so->rx.ll_dl) return 1; /* PDU size > default => try max_pdu_size */ if (so->rx.len > so->rx.buflen && so->rx.buflen < max_pdu_size) { u8 *newbuf = kmalloc(max_pdu_size, GFP_ATOMIC); if (newbuf) { so->rx.buf = newbuf; so->rx.buflen = max_pdu_size; } } if (so->rx.len > so->rx.buflen) { /* send FC frame with overflow status */ isotp_send_fc(sk, ae, ISOTP_FC_OVFLW); return 1; } /* copy the first received data bytes */ so->rx.idx = 0; for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++) so->rx.buf[so->rx.idx++] = cf->data[i]; /* initial setup for this pdu reception */ so->rx.sn = 1; so->rx.state = ISOTP_WAIT_DATA; /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) return 0; /* send our first FC frame */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; } static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, struct sk_buff *skb) { struct isotp_sock *so = isotp_sk(sk); struct sk_buff *nskb; int i; if (so->rx.state != ISOTP_WAIT_DATA) return 0; /* drop if timestamp gap is less than force_rx_stmin nano secs */ if (so->opt.flags & CAN_ISOTP_FORCE_RXSTMIN) { if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) < so->force_rx_stmin) return 0; so->lastrxcf_tstamp = skb->tstamp; } hrtimer_cancel(&so->rxtimer); /* CFs are never longer than the FF */ if (cf->len > so->rx.ll_dl) return 1; /* CFs have usually the LL_DL length */ if (cf->len < so->rx.ll_dl) { /* this is only allowed for the last CF */ if (so->rx.len - so->rx.idx > so->rx.ll_dl - ae - N_PCI_SZ) return 1; } if ((cf->data[ae] & 0x0F) != so->rx.sn) { /* wrong sn detected - report 'illegal byte sequence' */ sk->sk_err = EILSEQ; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; return 1; } so->rx.sn++; so->rx.sn %= 16; for (i = ae + N_PCI_SZ; i < cf->len; i++) { so->rx.buf[so->rx.idx++] = cf->data[i]; if (so->rx.idx >= so->rx.len) break; } if (so->rx.idx >= so->rx.len) { /* we are done */ so->rx.state = ISOTP_IDLE; if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, i + 1, so->opt.rxpad_content)) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 1; } nskb = alloc_skb(so->rx.len, gfp_any()); if (!nskb) return 1; memcpy(skb_put(nskb, so->rx.len), so->rx.buf, so->rx.len); nskb->tstamp = skb->tstamp; nskb->dev = skb->dev; isotp_rcv_skb(nskb, sk); return 0; } /* perform blocksize handling, if enabled */ if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { /* start rx timeout watchdog */ hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) return 0; /* we reached the specified blocksize so->rxfc.bs */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; } static void isotp_rcv(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; u8 n_pci_type, sf_dl; /* Strictly receive only frames with the configured MTU size * => clear separation of CAN2.0 / CAN FD transport channels */ if (skb->len != so->ll.mtu) return; cf = (struct canfd_frame *)skb->data; /* if enabled: check reception of my configured extended address */ if (ae && cf->data[0] != so->opt.rx_ext_address) return; n_pci_type = cf->data[ae] & 0xF0; /* Make sure the state changes and data structures stay consistent at * CAN frame reception time. This locking is not needed in real world * use cases but the inconsistency can be triggered with syzkaller. */ spin_lock(&so->rx_lock); if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) { /* check rx/tx path half duplex expectations */ if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) || (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC)) goto out_unlock; } switch (n_pci_type) { case N_PCI_FC: /* tx path: flow control frame containing the FC parameters */ isotp_rcv_fc(so, cf, ae); break; case N_PCI_SF: /* rx path: single frame * * As we do not have a rx.ll_dl configuration, we can only test * if the CAN frames payload length matches the LL_DL == 8 * requirements - no matter if it's CAN 2.0 or CAN FD */ /* get the SF_DL from the N_PCI byte */ sf_dl = cf->data[ae] & 0x0F; if (cf->len <= CAN_MAX_DLEN) { isotp_rcv_sf(sk, cf, SF_PCI_SZ4 + ae, skb, sf_dl); } else { if (can_is_canfd_skb(skb)) { /* We have a CAN FD frame and CAN_DL is greater than 8: * Only frames with the SF_DL == 0 ESC value are valid. * * If so take care of the increased SF PCI size * (SF_PCI_SZ8) to point to the message content behind * the extended SF PCI info and get the real SF_DL * length value from the formerly first data byte. */ if (sf_dl == 0) isotp_rcv_sf(sk, cf, SF_PCI_SZ8 + ae, skb, cf->data[SF_PCI_SZ4 + ae]); } } break; case N_PCI_FF: /* rx path: first frame */ isotp_rcv_ff(sk, cf, ae); break; case N_PCI_CF: /* rx path: consecutive frame */ isotp_rcv_cf(sk, cf, ae, skb); break; } out_unlock: spin_unlock(&so->rx_lock); } static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so, int ae, int off) { int pcilen = N_PCI_SZ + ae + off; int space = so->tx.ll_dl - pcilen; int num = min_t(int, so->tx.len - so->tx.idx, space); int i; cf->can_id = so->txid; cf->len = num + pcilen; if (num < space) { if (so->opt.flags & CAN_ISOTP_TX_PADDING) { /* user requested padding */ cf->len = padlen(cf->len); memset(cf->data, so->opt.txpad_content, cf->len); } else if (cf->len > CAN_MAX_DLEN) { /* mandatory padding for CAN FD frames */ cf->len = padlen(cf->len); memset(cf->data, CAN_ISOTP_DEFAULT_PAD_CONTENT, cf->len); } } for (i = 0; i < num; i++) cf->data[pcilen + i] = so->tx.buf[so->tx.idx++]; if (ae) cf->data[0] = so->opt.ext_address; } static void isotp_send_cframe(struct isotp_sock *so) { struct sock *sk = &so->sk; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; int can_send_ret; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) return; skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), GFP_ATOMIC); if (!skb) { dev_put(dev); return; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); /* create consecutive frame */ isotp_fill_dataframe(cf, so, ae, 0); /* place consecutive frame N_PCI in appropriate index */ cf->data[ae] = N_PCI_CF | so->tx.sn++; so->tx.sn %= 16; so->tx.bs++; cf->flags = so->ll.tx_flags; skb->dev = dev; can_skb_set_owner(skb, sk); /* cfecho should have been zero'ed by init/isotp_rcv_echo() */ if (so->cfecho) pr_notice_once("can-isotp: cfecho is %08X != 0\n", so->cfecho); /* set consecutive frame echo tag */ so->cfecho = *(u32 *)cf->data; /* send frame with local echo enabled */ can_send_ret = can_send(skb, 1); if (can_send_ret) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(can_send_ret)); if (can_send_ret == -ENOBUFS) pr_notice_once("can-isotp: tx queue is full\n"); } dev_put(dev); } static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so, int ae) { int i; int ff_pci_sz; cf->can_id = so->txid; cf->len = so->tx.ll_dl; if (ae) cf->data[0] = so->opt.ext_address; /* create N_PCI bytes with 12/32 bit FF_DL data length */ if (so->tx.len > MAX_12BIT_PDU_SIZE) { /* use 32 bit FF_DL notation */ cf->data[ae] = N_PCI_FF; cf->data[ae + 1] = 0; cf->data[ae + 2] = (u8)(so->tx.len >> 24) & 0xFFU; cf->data[ae + 3] = (u8)(so->tx.len >> 16) & 0xFFU; cf->data[ae + 4] = (u8)(so->tx.len >> 8) & 0xFFU; cf->data[ae + 5] = (u8)so->tx.len & 0xFFU; ff_pci_sz = FF_PCI_SZ32; } else { /* use 12 bit FF_DL notation */ cf->data[ae] = (u8)(so->tx.len >> 8) | N_PCI_FF; cf->data[ae + 1] = (u8)so->tx.len & 0xFFU; ff_pci_sz = FF_PCI_SZ12; } /* add first data bytes depending on ae */ for (i = ae + ff_pci_sz; i < so->tx.ll_dl; i++) cf->data[i] = so->tx.buf[so->tx.idx++]; so->tx.sn = 1; } static void isotp_rcv_echo(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf = (struct canfd_frame *)skb->data; /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) return; /* cancel local echo timeout */ hrtimer_cancel(&so->txtimer); /* local echo skb with consecutive frame has been consumed */ so->cfecho = 0; if (so->tx.idx >= so->tx.len) { /* we are done */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return; } if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { /* stop and wait for FC with timeout */ so->tx.state = ISOTP_WAIT_FC; hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { /* enable echo timeout handling */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); return; } /* start timer to send next consecutive frame with correct delay */ hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); } static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; /* don't handle timeouts in IDLE or SHUTDOWN state */ if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset tx state */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return HRTIMER_NORESTART; } static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txfrtimer); /* start echo timeout handling and cover below protocol error */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); /* cfecho should be consumed by isotp_rcv_echo() here */ if (so->tx.state == ISOTP_SENDING && !so->cfecho) isotp_send_cframe(so); return HRTIMER_NORESTART; } static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; int off; int err; if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { /* we do not support multiple buffers - for now */ if (msg->msg_flags & MSG_DONTWAIT) return -EAGAIN; if (so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_event_drop; } /* PDU size > default => try max_pdu_size */ if (size > so->tx.buflen && so->tx.buflen < max_pdu_size) { u8 *newbuf = kmalloc(max_pdu_size, GFP_KERNEL); if (newbuf) { so->tx.buf = newbuf; so->tx.buflen = max_pdu_size; } } if (!size || size > so->tx.buflen) { err = -EINVAL; goto err_out_drop; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; /* does the given data fit into a single frame for SF_BROADCAST? */ if ((isotp_bc_flags(so) == CAN_ISOTP_SF_BROADCAST) && (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) { err = -EINVAL; goto err_out_drop; } err = memcpy_from_msg(so->tx.buf, msg, size); if (err < 0) goto err_out_drop; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { err = -ENXIO; goto err_out_drop; } skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) { dev_put(dev); goto err_out_drop; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; so->tx.len = size; so->tx.idx = 0; cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); /* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ if (so->cfecho) pr_notice_once("can-isotp: uninit cfecho %08X\n", so->cfecho); /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { /* The message size generally fits into a SingleFrame - good. * * SF_DL ESC offset optimization: * * When TX_DL is greater 8 but the message would still fit * into a 8 byte CAN frame, we can omit the offset. * This prevents a protocol caused length extension from * CAN_DL = 8 to CAN_DL = 12 due to the SF_SL ESC handling. */ if (size <= CAN_MAX_DLEN - SF_PCI_SZ4 - ae) off = 0; isotp_fill_dataframe(cf, so, ae, off); /* place single frame N_PCI w/o length in appropriate index */ cf->data[ae] = N_PCI_SF; /* place SF_DL size value depending on the SF_DL ESC offset */ if (off) cf->data[SF_PCI_SZ4 + ae] = size; else cf->data[ae] |= size; /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ so->cfecho = *(u32 *)cf->data; } else { /* send first frame */ isotp_create_fframe(cf, so, ae); if (isotp_bc_flags(so) == CAN_ISOTP_CF_BROADCAST) { /* set timer for FC-less operation (STmin = 0) */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_set(0, so->force_tx_stmin); else so->tx_gap = ktime_set(0, so->frame_txtime); /* disable wait for FCs due to activated block size */ so->txfc.bs = 0; /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ so->cfecho = *(u32 *)cf->data; } else { /* standard flow control check */ so->tx.state = ISOTP_WAIT_FIRST_FC; /* start timeout for FC */ hrtimer_sec = ISOTP_FC_TIMEOUT; /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ so->cfecho = 0; } } hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), HRTIMER_MODE_REL_SOFT); /* send the first or only CAN frame */ cf->flags = so->ll.tx_flags; skb->dev = dev; skb->sk = sk; err = can_send(skb, 1); dev_put(dev); if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); /* no transmission -> no timeout monitoring */ hrtimer_cancel(&so->txtimer); /* reset consecutive frame echo tag */ so->cfecho = 0; goto err_out_drop; } if (wait_tx_done) { /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_event_drop; err = sock_error(sk); if (err) return err; } return size; err_event_drop: /* got signal: force tx state machine to be idle */ so->tx.state = ISOTP_IDLE; hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); err_out_drop: /* drop this PDU and unlock a potential wait queue */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return err; } static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; struct isotp_sock *so = isotp_sk(sk); int ret = 0; if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) return -EADDRNOTAVAIL; skb = skb_recv_datagram(sk, flags, &ret); if (!skb) return ret; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; ret = memcpy_to_msg(msg, skb->data, size); if (ret < 0) goto out_err; sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(ISOTP_MIN_NAMELEN); msg->msg_namelen = ISOTP_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* set length of return value */ ret = (flags & MSG_TRUNC) ? skb->len : size; out_err: skb_free_datagram(sk, skb); return ret; } static int isotp_release(struct socket *sock) { struct sock *sk = sock->sk; struct isotp_sock *so; struct net *net; if (!sk) return 0; so = isotp_sk(sk); net = sock_net(sk); /* wait for complete transmission of current pdu */ while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) ; /* force state machines to be idle also when a signal occurred */ so->tx.state = ISOTP_SHUTDOWN; so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { spin_unlock(&isotp_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&isotp_notifier_lock); } list_del(&so->notifier); spin_unlock(&isotp_notifier_lock); lock_sock(sk); /* remove current filters & unregister */ if (so->bound) { if (so->ifindex) { struct net_device *dev; dev = dev_get_by_index(net, so->ifindex); if (dev) { if (isotp_register_rxid(so)) can_rx_unregister(net, dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); can_rx_unregister(net, dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); dev_put(dev); synchronize_rcu(); } } } hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->rxtimer); so->ifindex = 0; so->bound = 0; if (so->rx.buf != so->rx.sbuf) kfree(so->rx.buf); if (so->tx.buf != so->tx.sbuf) kfree(so->tx.buf); sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); struct net *net = sock_net(sk); int ifindex; struct net_device *dev; canid_t tx_id = addr->can_addr.tp.tx_id; canid_t rx_id = addr->can_addr.tp.rx_id; int err = 0; int notify_enetdown = 0; if (len < ISOTP_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; /* sanitize tx CAN identifier */ if (tx_id & CAN_EFF_FLAG) tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); else tx_id &= CAN_SFF_MASK; /* give feedback on wrong CAN-ID value */ if (tx_id != addr->can_addr.tp.tx_id) return -EINVAL; /* sanitize rx CAN identifier (if needed) */ if (isotp_register_rxid(so)) { if (rx_id & CAN_EFF_FLAG) rx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); else rx_id &= CAN_SFF_MASK; /* give feedback on wrong CAN-ID value */ if (rx_id != addr->can_addr.tp.rx_id) return -EINVAL; } if (!addr->can_ifindex) return -ENODEV; lock_sock(sk); if (so->bound) { err = -EINVAL; goto out; } /* ensure different CAN IDs when the rx_id is to be registered */ if (isotp_register_rxid(so) && rx_id == tx_id) { err = -EADDRNOTAVAIL; goto out; } dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { dev_put(dev); err = -ENODEV; goto out; } if (dev->mtu < so->ll.mtu) { dev_put(dev); err = -EINVAL; goto out; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; ifindex = dev->ifindex; if (isotp_register_rxid(so)) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk); /* no consecutive frame echo skb in flight */ so->cfecho = 0; /* register for echo skb's */ can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), isotp_rcv_echo, sk, "isotpe", sk); dev_put(dev); /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; so->txid = tx_id; so->bound = 1; out: release_sock(sk); if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } return err; } static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); if (peer) return -EOPNOTSUPP; memset(addr, 0, ISOTP_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = so->ifindex; addr->can_addr.tp.rx_id = so->rxid; addr->can_addr.tp.tx_id = so->txid; return ISOTP_MIN_NAMELEN; } static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int ret = 0; if (so->bound) return -EISCONN; switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) return -EINVAL; if (copy_from_sockptr(&so->opt, optval, optlen)) return -EFAULT; /* no separate rx_ext_address is given => use ext_address */ if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR)) so->opt.rx_ext_address = so->opt.ext_address; /* these broadcast flags are not allowed together */ if (isotp_bc_flags(so) == ISOTP_ALL_BC_FLAGS) { /* CAN_ISOTP_SF_BROADCAST is prioritized */ so->opt.flags &= ~CAN_ISOTP_CF_BROADCAST; /* give user feedback on wrong config attempt */ ret = -EINVAL; } /* check for frame_txtime changes (0 => no changes) */ if (so->opt.frame_txtime) { if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO) so->frame_txtime = 0; else so->frame_txtime = so->opt.frame_txtime; } break; case CAN_ISOTP_RECV_FC: if (optlen != sizeof(struct can_isotp_fc_options)) return -EINVAL; if (copy_from_sockptr(&so->rxfc, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_TX_STMIN: if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_RX_STMIN: if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_LL_OPTS: if (optlen == sizeof(struct can_isotp_ll_options)) { struct can_isotp_ll_options ll; if (copy_from_sockptr(&ll, optval, optlen)) return -EFAULT; /* check for correct ISO 11898-1 DLC data length */ if (ll.tx_dl != padlen(ll.tx_dl)) return -EINVAL; if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU) return -EINVAL; if (ll.mtu == CAN_MTU && (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0)) return -EINVAL; memcpy(&so->ll, &ll, sizeof(ll)); /* set ll_dl for tx path to similar place as for rx */ so->tx.ll_dl = ll.tx_dl; } else { return -EINVAL; } break; default: ret = -ENOPROTOOPT; } return ret; } static int isotp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int ret; if (level != SOL_CAN_ISOTP) return -EINVAL; lock_sock(sk); ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen); release_sock(sk); return ret; } static int isotp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int len; void *val; if (level != SOL_CAN_ISOTP) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case CAN_ISOTP_OPTS: len = min_t(int, len, sizeof(struct can_isotp_options)); val = &so->opt; break; case CAN_ISOTP_RECV_FC: len = min_t(int, len, sizeof(struct can_isotp_fc_options)); val = &so->rxfc; break; case CAN_ISOTP_TX_STMIN: len = min_t(int, len, sizeof(u32)); val = &so->force_tx_stmin; break; case CAN_ISOTP_RX_STMIN: len = min_t(int, len, sizeof(u32)); val = &so->force_rx_stmin; break; case CAN_ISOTP_LL_OPTS: len = min_t(int, len, sizeof(struct can_isotp_ll_options)); val = &so->ll; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, val, len)) return -EFAULT; return 0; } static void isotp_notify(struct isotp_sock *so, unsigned long msg, struct net_device *dev) { struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) return; if (so->ifindex != dev->ifindex) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); can_rx_unregister(dev_net(dev), dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); } so->ifindex = 0; so->bound = 0; release_sock(sk); sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; } } static int isotp_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&isotp_notifier_lock); list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { spin_unlock(&isotp_notifier_lock); isotp_notify(isotp_busy_notifier, msg, dev); spin_lock(&isotp_notifier_lock); } isotp_busy_notifier = NULL; spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } static int isotp_init(struct sock *sk) { struct isotp_sock *so = isotp_sk(sk); so->ifindex = 0; so->bound = 0; so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS; so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS; so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN; so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX; so->ll.mtu = CAN_ISOTP_DEFAULT_LL_MTU; so->ll.tx_dl = CAN_ISOTP_DEFAULT_LL_TX_DL; so->ll.tx_flags = CAN_ISOTP_DEFAULT_LL_TX_FLAGS; /* set ll_dl for tx path to similar place as for rx */ so->tx.ll_dl = so->ll.tx_dl; so->rx.state = ISOTP_IDLE; so->tx.state = ISOTP_IDLE; so->rx.buf = so->rx.sbuf; so->tx.buf = so->tx.sbuf; so->rx.buflen = ARRAY_SIZE(so->rx.sbuf); so->tx.buflen = ARRAY_SIZE(so->tx.sbuf); hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->rxtimer.function = isotp_rx_timer_handler; hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txtimer.function = isotp_tx_timer_handler; hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txfrtimer.function = isotp_txfr_timer_handler; init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); spin_lock(&isotp_notifier_lock); list_add_tail(&so->notifier, &isotp_notifier_list); spin_unlock(&isotp_notifier_lock); return 0; } static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); poll_wait(file, &so->wait, wait); /* Check for false positives due to TX state */ if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) mask &= ~(EPOLLOUT | EPOLLWRNORM); return mask; } static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops isotp_ops = { .family = PF_CAN, .release = isotp_release, .bind = isotp_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = isotp_setsockopt, .getsockopt = isotp_getsockopt, .sendmsg = isotp_sendmsg, .recvmsg = isotp_recvmsg, .mmap = sock_no_mmap, }; static struct proto isotp_proto __read_mostly = { .name = "CAN_ISOTP", .owner = THIS_MODULE, .obj_size = sizeof(struct isotp_sock), .init = isotp_init, }; static const struct can_proto isotp_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_ISOTP, .ops = &isotp_ops, .prot = &isotp_proto, }; static struct notifier_block canisotp_notifier = { .notifier_call = isotp_notifier }; static __init int isotp_module_init(void) { int err; max_pdu_size = max_t(unsigned int, max_pdu_size, MAX_12BIT_PDU_SIZE); max_pdu_size = min_t(unsigned int, max_pdu_size, MAX_PDU_SIZE); pr_info("can: isotp protocol (max_pdu_size %d)\n", max_pdu_size); err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); else register_netdevice_notifier(&canisotp_notifier); return err; } static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); module_exit(isotp_module_exit); |
| 93 93 93 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H #include <linux/context_tracking_state.h> #include <linux/sched.h> /* * Common vtime APIs */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING extern void vtime_account_kernel(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } static inline void vtime_guest_exit(struct task_struct *tsk) { } static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); extern void vtime_account_softirq(struct task_struct *tsk); extern void vtime_account_hardirq(struct task_struct *tsk); extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } static inline void vtime_account_softirq(struct task_struct *tsk) { } static inline void vtime_account_hardirq(struct task_struct *tsk) { } static inline void vtime_flush(struct task_struct *tsk) { } #endif /* * vtime_accounting_enabled_this_cpu() definitions/declarations */ #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } extern void vtime_task_switch(struct task_struct *prev); static __always_inline void vtime_account_guest_enter(void) { vtime_account_kernel(current); current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { vtime_account_kernel(current); current->flags &= ~PF_VCPU; } #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) /* * Checks if vtime is enabled on some CPU. Cputime readers want to be careful * in that case and compute the tickless cputime. * For now vtime state is tied to context tracking. We might want to decouple * those later if necessary. */ static inline bool vtime_accounting_enabled(void) { return context_tracking_enabled(); } static inline bool vtime_accounting_enabled_cpu(int cpu) { return context_tracking_enabled_cpu(cpu); } static inline bool vtime_accounting_enabled_this_cpu(void) { return context_tracking_enabled_this_cpu(); } extern void vtime_task_switch_generic(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { if (vtime_accounting_enabled_this_cpu()) vtime_task_switch_generic(prev); } static __always_inline void vtime_account_guest_enter(void) { if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; } #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } static __always_inline void vtime_account_guest_enter(void) { current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { current->flags &= ~PF_VCPU; } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING extern void irqtime_account_irq(struct task_struct *tsk, unsigned int offset); #else static inline void irqtime_account_irq(struct task_struct *tsk, unsigned int offset) { } #endif static inline void account_softirq_enter(struct task_struct *tsk) { vtime_account_irq(tsk, SOFTIRQ_OFFSET); irqtime_account_irq(tsk, SOFTIRQ_OFFSET); } static inline void account_softirq_exit(struct task_struct *tsk) { vtime_account_softirq(tsk); irqtime_account_irq(tsk, 0); } static inline void account_hardirq_enter(struct task_struct *tsk) { vtime_account_irq(tsk, HARDIRQ_OFFSET); irqtime_account_irq(tsk, HARDIRQ_OFFSET); } static inline void account_hardirq_exit(struct task_struct *tsk) { vtime_account_hardirq(tsk); irqtime_account_irq(tsk, 0); } #endif /* _LINUX_KERNEL_VTIME_H */ |
| 215 3 47 176 218 218 179 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 | /* * memfd_create system call and file sealing support * * Code was originally included in shmem.c, and broken out to facilitate * use by hugetlbfs as well as tmpfs. * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/khugepaged.h> #include <linux/syscalls.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/memfd.h> #include <linux/pid_namespace.h> #include <uapi/linux/memfd.h> /* * We need a tag: a new tag would expand every xa_node by 8 bytes, * so reuse a tag which we firmly believe is never set or cleared on tmpfs * or hugetlbfs because they are memory only filesystems. */ #define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE #define LAST_SCAN 4 /* about 150ms max */ static bool memfd_folio_has_extra_refs(struct folio *folio) { return folio_ref_count(folio) - folio_mapcount(folio) != folio_nr_pages(folio); } static void memfd_tag_pins(struct xa_state *xas) { struct folio *folio; int latency = 0; lru_add_drain(); xas_lock_irq(xas); xas_for_each(xas, folio, ULONG_MAX) { if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio)) xas_set_mark(xas, MEMFD_TAG_PINNED); if (++latency < XA_CHECK_SCHED) continue; latency = 0; xas_pause(xas); xas_unlock_irq(xas); cond_resched(); xas_lock_irq(xas); } xas_unlock_irq(xas); } /* * This is a helper function used by memfd_pin_user_pages() in GUP (gup.c). * It is mainly called to allocate a folio in a memfd when the caller * (memfd_pin_folios()) cannot find a folio in the page cache at a given * index in the mapping. */ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { #ifdef CONFIG_HUGETLB_PAGE struct folio *folio; gfp_t gfp_mask; int err; if (is_file_hugepages(memfd)) { /* * The folio would most likely be accessed by a DMA driver, * therefore, we have zone memory constraints where we can * alloc from. Also, the folio will be pinned for an indefinite * amount of time, so it is not expected to be migrated away. */ struct hstate *h = hstate_file(memfd); gfp_mask = htlb_alloc_mask(h); gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE); idx >>= huge_page_order(h); folio = alloc_hugetlb_folio_reserve(h, numa_node_id(), NULL, gfp_mask); if (folio) { err = hugetlb_add_to_page_cache(folio, memfd->f_mapping, idx); if (err) { folio_put(folio); return ERR_PTR(err); } folio_unlock(folio); return folio; } return ERR_PTR(-ENOMEM); } #endif return shmem_read_folio(memfd->f_mapping, idx); } /* * Setting SEAL_WRITE requires us to verify there's no pending writer. However, * via get_user_pages(), drivers might have some pending I/O without any active * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all folios * and see whether it has an elevated ref-count. If so, we tag them and wait for * them to be dropped. * The caller must guarantee that no new user will acquire writable references * to those folios to avoid races. */ static int memfd_wait_for_pins(struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; int error, scan; memfd_tag_pins(&xas); error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { int latency = 0; if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; if (!scan) lru_add_drain_all(); else if (schedule_timeout_killable((HZ << scan) / 200)) scan = LAST_SCAN; xas_set(&xas, 0); xas_lock_irq(&xas); xas_for_each_marked(&xas, folio, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true; if (!xa_is_value(folio) && memfd_folio_has_extra_refs(folio)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still * found folios pinned. */ if (scan == LAST_SCAN) error = -EBUSY; else clear = false; } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED); if (++latency < XA_CHECK_SCHED) continue; latency = 0; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } return error; } static unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; #ifdef CONFIG_HUGETLBFS if (is_file_hugepages(file)) return &HUGETLBFS_I(file_inode(file))->seals; #endif return NULL; } #define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_EXEC | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ F_SEAL_WRITE | \ F_SEAL_FUTURE_WRITE) static int memfd_add_seals(struct file *file, unsigned int seals) { struct inode *inode = file_inode(file); unsigned int *file_seals; int error; /* * SEALING * Sealing allows multiple parties to share a tmpfs or hugetlbfs file * but restrict access to a specific subset of file operations. Seals * can only be added, but never removed. This way, mutually untrusted * parties can share common memory regions with a well-defined policy. * A malicious peer can thus never perform unwanted operations on a * shared object. * * Seals are only supported on special tmpfs or hugetlbfs files and * always affect the whole underlying inode. Once a seal is set, it * may prevent some kinds of access to the file. Currently, the * following seals are defined: * SEAL_SEAL: Prevent further seals from being set on this file * SEAL_SHRINK: Prevent the file from shrinking * SEAL_GROW: Prevent the file from growing * SEAL_WRITE: Prevent write access to the file * SEAL_EXEC: Prevent modification of the exec bits in the file mode * * As we don't require any trust relationship between two parties, we * must prevent seals from being removed. Therefore, sealing a file * only adds a given set of seals to the file, it never touches * existing seals. Furthermore, the "setting seals"-operation can be * sealed itself, which basically prevents any further seal from being * added. * * Semantics of sealing are only defined on volatile files. Only * anonymous tmpfs and hugetlbfs files support sealing. More * importantly, seals are never written to disk. Therefore, there's * no plan to support it on other file types. */ if (!(file->f_mode & FMODE_WRITE)) return -EPERM; if (seals & ~(unsigned int)F_ALL_SEALS) return -EINVAL; inode_lock(inode); file_seals = memfd_file_seals_ptr(file); if (!file_seals) { error = -EINVAL; goto unlock; } if (*file_seals & F_SEAL_SEAL) { error = -EPERM; goto unlock; } if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) { error = mapping_deny_writable(file->f_mapping); if (error) goto unlock; error = memfd_wait_for_pins(file->f_mapping); if (error) { mapping_allow_writable(file->f_mapping); goto unlock; } } /* * SEAL_EXEC implys SEAL_WRITE, making W^X from the start. */ if (seals & F_SEAL_EXEC && inode->i_mode & 0111) seals |= F_SEAL_SHRINK|F_SEAL_GROW|F_SEAL_WRITE|F_SEAL_FUTURE_WRITE; *file_seals |= seals; error = 0; unlock: inode_unlock(inode); return error; } static int memfd_get_seals(struct file *file) { unsigned int *seals = memfd_file_seals_ptr(file); return seals ? *seals : -EINVAL; } long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { long error; switch (cmd) { case F_ADD_SEALS: error = memfd_add_seals(file, arg); break; case F_GET_SEALS: error = memfd_get_seals(file); break; default: error = -EINVAL; break; } return error; } #define MFD_NAME_PREFIX "memfd:" #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) #define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB | MFD_NOEXEC_SEAL | MFD_EXEC) static int check_sysctl_memfd_noexec(unsigned int *flags) { #ifdef CONFIG_SYSCTL struct pid_namespace *ns = task_active_pid_ns(current); int sysctl = pidns_memfd_noexec_scope(ns); if (!(*flags & (MFD_EXEC | MFD_NOEXEC_SEAL))) { if (sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL) *flags |= MFD_NOEXEC_SEAL; else *flags |= MFD_EXEC; } if (!(*flags & MFD_NOEXEC_SEAL) && sysctl >= MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED) { pr_err_ratelimited( "%s[%d]: memfd_create() requires MFD_NOEXEC_SEAL with vm.memfd_noexec=%d\n", current->comm, task_pid_nr(current), sysctl); return -EACCES; } #endif return 0; } static inline bool is_write_sealed(unsigned int seals) { return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); } static int check_write_seal(unsigned long *vm_flags_ptr) { unsigned long vm_flags = *vm_flags_ptr; unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE); /* If a private matting then writability is irrelevant. */ if (!(mask & VM_SHARED)) return 0; /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * write seals are active. */ if (mask & VM_WRITE) return -EPERM; /* * This is a read-only mapping, disallow mprotect() from making a * write-sealed mapping writable in future. */ *vm_flags_ptr &= ~VM_MAYWRITE; return 0; } int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr) { int err = 0; unsigned int *seals_ptr = memfd_file_seals_ptr(file); unsigned int seals = seals_ptr ? *seals_ptr : 0; if (is_write_sealed(seals)) err = check_write_seal(vm_flags_ptr); return err; } static int sanitize_flags(unsigned int *flags_ptr) { unsigned int flags = *flags_ptr; if (!(flags & MFD_HUGETLB)) { if (flags & ~(unsigned int)MFD_ALL_FLAGS) return -EINVAL; } else { /* Allow huge page size encoding in flags. */ if (flags & ~(unsigned int)(MFD_ALL_FLAGS | (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) return -EINVAL; } /* Invalid if both EXEC and NOEXEC_SEAL are set.*/ if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL)) return -EINVAL; return check_sysctl_memfd_noexec(flags_ptr); } static char *alloc_name(const char __user *uname) { int error; char *name; long len; name = kmalloc(NAME_MAX + 1, GFP_KERNEL); if (!name) return ERR_PTR(-ENOMEM); strcpy(name, MFD_NAME_PREFIX); /* returned length does not include terminating zero */ len = strncpy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, MFD_NAME_MAX_LEN + 1); if (len < 0) { error = -EFAULT; goto err_name; } else if (len > MFD_NAME_MAX_LEN) { error = -EINVAL; goto err_name; } return name; err_name: kfree(name); return ERR_PTR(error); } static struct file *alloc_file(const char *name, unsigned int flags) { unsigned int *file_seals; struct file *file; if (flags & MFD_HUGETLB) { file = hugetlb_file_setup(name, 0, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); } else { file = shmem_file_setup(name, 0, VM_NORESERVE); } if (IS_ERR(file)) return file; file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; if (flags & MFD_NOEXEC_SEAL) { struct inode *inode = file_inode(file); inode->i_mode &= ~0111; file_seals = memfd_file_seals_ptr(file); if (file_seals) { *file_seals &= ~F_SEAL_SEAL; *file_seals |= F_SEAL_EXEC; } } else if (flags & MFD_ALLOW_SEALING) { /* MFD_EXEC and MFD_ALLOW_SEALING are set */ file_seals = memfd_file_seals_ptr(file); if (file_seals) *file_seals &= ~F_SEAL_SEAL; } return file; } SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags) { struct file *file; int fd, error; char *name; error = sanitize_flags(&flags); if (error < 0) return error; name = alloc_name(uname); if (IS_ERR(name)) return PTR_ERR(name); fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); if (fd < 0) { error = fd; goto err_name; } file = alloc_file(name, flags); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_fd; } fd_install(fd, file); kfree(name); return fd; err_fd: put_unused_fd(fd); err_name: kfree(name); return error; } |
| 11 248 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason); DEFINE_DROP_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SKB_DROP_REASON_##reason, #reason }, #define FNe(reason) { SKB_DROP_REASON_##reason, #reason } /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk), TP_ARGS(skb, location, reason, rx_sk), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) __field(void *, rx_sk) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->rx_sk = rx_sk; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->rx_sk, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); #undef FN #undef FNe TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr) __field( void *, location) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; ), TP_printk("skbaddr=%p location=%pS", __entry->skbaddr, __entry->location) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 192 194 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void wb_stat_mod(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { wb_stat_mod(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } /* BDI ratio is expressed as part per 1000000 for finer granularity. */ #define BDI_RATIO_SCALE 10000 u64 bdi_get_min_bytes(struct backing_dev_info *bdi); u64 bdi_get_max_bytes(struct backing_dev_info *bdi); int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio); int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes); int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes); int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit); /* * Flags in backing_dev_info::capability * * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages * should contribute to accounting * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ #define BDI_CAP_WRITEBACK (1 << 0) #define BDI_CAP_WRITEBACK_ACCT (1 << 1) #define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; int bdi_init(struct backing_dev_info *bdi); /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } struct backing_dev_info *inode_to_bdi(struct inode *inode); static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * Cgroup writeback requires support from the filesystem. Also, both memcg and * iocg have to be on the default hierarchy. Test whether all conditions are * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { /* * If wbc does not have inode attached, it means cgroup writeback was * disabled when wbc started. Just use the default wb in that case. */ return wbc->wb ? wbc->wb : &inode_to_bdi(inode)->wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback *inode_to_wb_wbc( struct inode *inode, struct writeback_control *wbc) { return inode_to_wb(inode); } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } #endif /* CONFIG_CGROUP_WRITEBACK */ const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 56 846 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 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 #include <linux/export.h> #include <linux/bitops.h> #include <asm/types.h> /** * hweightN - returns the hamming weight of a N-bit word * @x: the word to weigh * * The Hamming Weight of a number is the total number of bits set in it. */ unsigned int __sw_hweight32(unsigned int w) { #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; w = (w & 0x33333333) + ((w >> 2) & 0x33333333); w = (w + (w >> 4)) & 0x0f0f0f0f; return (w * 0x01010101) >> 24; #else unsigned int res = w - ((w >> 1) & 0x55555555); res = (res & 0x33333333) + ((res >> 2) & 0x33333333); res = (res + (res >> 4)) & 0x0F0F0F0F; res = res + (res >> 8); return (res + (res >> 16)) & 0x000000FF; #endif } EXPORT_SYMBOL(__sw_hweight32); unsigned int __sw_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } EXPORT_SYMBOL(__sw_hweight16); unsigned int __sw_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } EXPORT_SYMBOL(__sw_hweight8); unsigned long __sw_hweight64(__u64 w) { #if BITS_PER_LONG == 32 return __sw_hweight32((unsigned int)(w >> 32)) + __sw_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul); w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful; return (w * 0x0101010101010101ul) >> 56; #else __u64 res = w - ((w >> 1) & 0x5555555555555555ul); res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; res = res + (res >> 8); res = res + (res >> 16); return (res + (res >> 32)) & 0x00000000000000FFul; #endif #endif } EXPORT_SYMBOL(__sw_hweight64); |
| 93 93 92 19 1 96 143 80 95 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ARM_ARM64_KVM_H #include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm /* * Tracepoints for entry/exit to guest */ TRACE_EVENT(kvm_entry, TP_PROTO(unsigned long vcpu_pc), TP_ARGS(vcpu_pc), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; ), TP_printk("PC: 0x%016lx", __entry->vcpu_pc) ); TRACE_EVENT(kvm_exit, TP_PROTO(int ret, unsigned int esr_ec, unsigned long vcpu_pc), TP_ARGS(ret, esr_ec, vcpu_pc), TP_STRUCT__entry( __field( int, ret ) __field( unsigned int, esr_ec ) __field( unsigned long, vcpu_pc ) ), TP_fast_assign( __entry->ret = ARM_EXCEPTION_CODE(ret); __entry->esr_ec = ARM_EXCEPTION_IS_TRAP(ret) ? esr_ec : 0; __entry->vcpu_pc = vcpu_pc; ), TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx", __print_symbolic(__entry->ret, kvm_arm_exception_type), __entry->esr_ec, __print_symbolic(__entry->esr_ec, kvm_arm_exception_class), __entry->vcpu_pc) ); TRACE_EVENT(kvm_guest_fault, TP_PROTO(unsigned long vcpu_pc, unsigned long hsr, unsigned long hxfar, unsigned long long ipa), TP_ARGS(vcpu_pc, hsr, hxfar, ipa), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, hsr ) __field( unsigned long, hxfar ) __field( unsigned long long, ipa ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->hsr = hsr; __entry->hxfar = hxfar; __entry->ipa = ipa; ), TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx", __entry->ipa, __entry->hsr, __entry->hxfar, __entry->vcpu_pc) ); TRACE_EVENT(kvm_access_fault, TP_PROTO(unsigned long ipa), TP_ARGS(ipa), TP_STRUCT__entry( __field( unsigned long, ipa ) ), TP_fast_assign( __entry->ipa = ipa; ), TP_printk("IPA: %lx", __entry->ipa) ); TRACE_EVENT(kvm_irq_line, TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), TP_ARGS(type, vcpu_idx, irq_num, level), TP_STRUCT__entry( __field( unsigned int, type ) __field( int, vcpu_idx ) __field( int, irq_num ) __field( int, level ) ), TP_fast_assign( __entry->type = type; __entry->vcpu_idx = vcpu_idx; __entry->irq_num = irq_num; __entry->level = level; ), TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d", (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" : (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" : (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN", __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level) ); TRACE_EVENT(kvm_mmio_emulate, TP_PROTO(unsigned long vcpu_pc, unsigned long instr, unsigned long cpsr), TP_ARGS(vcpu_pc, instr, cpsr), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, instr ) __field( unsigned long, cpsr ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->instr = instr; __entry->cpsr = cpsr; ), TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)", __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); TRACE_EVENT(kvm_mmio_nisv, TP_PROTO(unsigned long vcpu_pc, unsigned long esr, unsigned long far, unsigned long ipa), TP_ARGS(vcpu_pc, esr, far, ipa), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, esr ) __field( unsigned long, far ) __field( unsigned long, ipa ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->esr = esr; __entry->far = far; __entry->ipa = ipa; ), TP_printk("ipa %#016lx, esr %#016lx, far %#016lx, pc %#016lx", __entry->ipa, __entry->esr, __entry->far, __entry->vcpu_pc) ); TRACE_EVENT(kvm_set_way_flush, TP_PROTO(unsigned long vcpu_pc, bool cache), TP_ARGS(vcpu_pc, cache), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( bool, cache ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->cache = cache; ), TP_printk("S/W flush at 0x%016lx (cache %s)", __entry->vcpu_pc, __entry->cache ? "on" : "off") ); TRACE_EVENT(kvm_toggle_cache, TP_PROTO(unsigned long vcpu_pc, bool was, bool now), TP_ARGS(vcpu_pc, was, now), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( bool, was ) __field( bool, now ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->was = was; __entry->now = now; ), TP_printk("VM op at 0x%016lx (cache was %s, now %s)", __entry->vcpu_pc, __entry->was ? "on" : "off", __entry->now ? "on" : "off") ); /* * Tracepoints for arch_timer */ TRACE_EVENT(kvm_timer_update_irq, TP_PROTO(unsigned long vcpu_id, __u32 irq, int level), TP_ARGS(vcpu_id, irq, level), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( __u32, irq ) __field( int, level ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->irq = irq; __entry->level = level; ), TP_printk("VCPU: %ld, IRQ %d, level %d", __entry->vcpu_id, __entry->irq, __entry->level) ); TRACE_EVENT(kvm_get_timer_map, TP_PROTO(unsigned long vcpu_id, struct timer_map *map), TP_ARGS(vcpu_id, map), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( int, direct_vtimer ) __field( int, direct_ptimer ) __field( int, emul_vtimer ) __field( int, emul_ptimer ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->direct_vtimer = arch_timer_ctx_index(map->direct_vtimer); __entry->direct_ptimer = (map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1; __entry->emul_vtimer = (map->emul_vtimer) ? arch_timer_ctx_index(map->emul_vtimer) : -1; __entry->emul_ptimer = (map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1; ), TP_printk("VCPU: %ld, dv: %d, dp: %d, ev: %d, ep: %d", __entry->vcpu_id, __entry->direct_vtimer, __entry->direct_ptimer, __entry->emul_vtimer, __entry->emul_ptimer) ); TRACE_EVENT(kvm_timer_save_state, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( unsigned long, ctl ) __field( unsigned long long, cval ) __field( int, timer_idx ) ), TP_fast_assign( __entry->ctl = timer_get_ctl(ctx); __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk(" CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", __entry->ctl, __entry->cval, __entry->timer_idx) ); TRACE_EVENT(kvm_timer_restore_state, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( unsigned long, ctl ) __field( unsigned long long, cval ) __field( int, timer_idx ) ), TP_fast_assign( __entry->ctl = timer_get_ctl(ctx); __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk("CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", __entry->ctl, __entry->cval, __entry->timer_idx) ); TRACE_EVENT(kvm_timer_hrtimer_expire, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( int, timer_idx ) ), TP_fast_assign( __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk("arch_timer_ctx_index: %d", __entry->timer_idx) ); TRACE_EVENT(kvm_timer_emulate, TP_PROTO(struct arch_timer_context *ctx, bool should_fire), TP_ARGS(ctx, should_fire), TP_STRUCT__entry( __field( int, timer_idx ) __field( bool, should_fire ) ), TP_fast_assign( __entry->timer_idx = arch_timer_ctx_index(ctx); __entry->should_fire = should_fire; ), TP_printk("arch_timer_ctx_index: %d (should_fire: %d)", __entry->timer_idx, __entry->should_fire) ); TRACE_EVENT(kvm_nested_eret, TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2, unsigned long spsr_el2), TP_ARGS(vcpu, elr_el2, spsr_el2), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(unsigned long, elr_el2) __field(unsigned long, spsr_el2) __field(unsigned long, target_mode) __field(unsigned long, hcr_el2) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->elr_el2 = elr_el2; __entry->spsr_el2 = spsr_el2; __entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT); __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); ), TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", __entry->elr_el2, __entry->spsr_el2, __print_symbolic(__entry->target_mode, kvm_mode_names), __entry->hcr_el2) ); TRACE_EVENT(kvm_inject_nested_exception, TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type), TP_ARGS(vcpu, esr_el2, type), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(unsigned long, esr_el2) __field(int, type) __field(unsigned long, spsr_el2) __field(unsigned long, pc) __field(unsigned long, source_mode) __field(unsigned long, hcr_el2) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->esr_el2 = esr_el2; __entry->type = type; __entry->spsr_el2 = *vcpu_cpsr(vcpu); __entry->pc = *vcpu_pc(vcpu); __entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); ), TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", __print_symbolic(__entry->type, kvm_exception_type_names), __entry->esr_el2, __entry->pc, __entry->spsr_el2, __print_symbolic(__entry->source_mode, kvm_mode_names), __entry->hcr_el2) ); TRACE_EVENT(kvm_forward_sysreg_trap, TP_PROTO(struct kvm_vcpu *vcpu, u32 sysreg, bool is_read), TP_ARGS(vcpu, sysreg, is_read), TP_STRUCT__entry( __field(u64, pc) __field(u32, sysreg) __field(bool, is_read) ), TP_fast_assign( __entry->pc = *vcpu_pc(vcpu); __entry->sysreg = sysreg; __entry->is_read = is_read; ), TP_printk("%llx %c (%d,%d,%d,%d,%d)", __entry->pc, __entry->is_read ? 'R' : 'W', sys_reg_Op0(__entry->sysreg), sys_reg_Op1(__entry->sysreg), sys_reg_CRn(__entry->sysreg), sys_reg_CRm(__entry->sysreg), sys_reg_Op2(__entry->sysreg)) ); #endif /* _TRACE_ARM_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace_arm /* This part must be outside protection */ #include <trace/define_trace.h> |
| 167 168 168 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 | // SPDX-License-Identifier: GPL-2.0-only /* * Fixmap manipulation code */ #include <linux/bug.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/libfdt.h> #include <linux/memory.h> #include <linux/mm.h> #include <linux/sizes.h> #include <asm/fixmap.h> #include <asm/kernel-pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> /* ensure that the fixmap region does not grow down into the PCI I/O region */ static_assert(FIXADDR_TOT_START > PCI_IO_END); #define NR_BM_PTE_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT) #define NR_BM_PMD_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PUD_SHIFT) static_assert(NR_BM_PMD_TABLES == 1); #define __BM_TABLE_IDX(addr, shift) \ (((addr) >> (shift)) - (FIXADDR_TOT_START >> (shift))) #define BM_PTE_TABLE_IDX(addr) __BM_TABLE_IDX(addr, PMD_SHIFT) static pte_t bm_pte[NR_BM_PTE_TABLES][PTRS_PER_PTE] __page_aligned_bss; static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused; static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused; static inline pte_t *fixmap_pte(unsigned long addr) { return &bm_pte[BM_PTE_TABLE_IDX(addr)][pte_index(addr)]; } static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr) { pmd_t pmd = READ_ONCE(*pmdp); pte_t *ptep; if (pmd_none(pmd)) { ptep = bm_pte[BM_PTE_TABLE_IDX(addr)]; __pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE | PMD_TABLE_AF); } } static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr, unsigned long end) { unsigned long next; pud_t pud = READ_ONCE(*pudp); pmd_t *pmdp; if (pud_none(pud)) __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE | PUD_TABLE_AF); pmdp = pmd_offset_kimg(pudp, addr); do { next = pmd_addr_end(addr, end); early_fixmap_init_pte(pmdp, addr); } while (pmdp++, addr = next, addr != end); } static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end) { p4d_t p4d = READ_ONCE(*p4dp); pud_t *pudp; if (CONFIG_PGTABLE_LEVELS > 3 && !p4d_none(p4d) && p4d_page_paddr(p4d) != __pa_symbol(bm_pud)) { /* * We only end up here if the kernel mapping and the fixmap * share the top level pgd entry, which should only happen on * 16k/4 levels configurations. */ BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); } if (p4d_none(p4d)) __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE | P4D_TABLE_AF); pudp = pud_offset_kimg(p4dp, addr); early_fixmap_init_pmd(pudp, addr, end); } /* * The p*d_populate functions call virt_to_phys implicitly so they can't be used * directly on kernel symbols (bm_p*d). This function is called too early to use * lm_alias so __p*d_populate functions must be used to populate with the * physical address from __pa_symbol. */ void __init early_fixmap_init(void) { unsigned long addr = FIXADDR_TOT_START; unsigned long end = FIXADDR_TOP; pgd_t *pgdp = pgd_offset_k(addr); p4d_t *p4dp = p4d_offset_kimg(pgdp, addr); early_fixmap_init_pud(p4dp, addr, end); } /* * Unusually, this is also called in IRQ context (ghes_iounmap_irq) so if we * ever need to use IPIs for TLB broadcasting, then we're in trouble here. */ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *ptep; BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); ptep = fixmap_pte(addr); if (pgprot_val(flags)) { __set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags)); } else { __pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) { const u64 dt_virt_base = __fix_to_virt(FIX_FDT); phys_addr_t dt_phys_base; int offset; void *dt_virt; /* * Check whether the physical FDT address is set and meets the minimum * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be * at least 8 bytes so that we can always access the magic and size * fields of the FDT header after mapping the first chunk, double check * here if that is indeed the case. */ BUILD_BUG_ON(MIN_FDT_ALIGN < 8); if (!dt_phys || dt_phys % MIN_FDT_ALIGN) return NULL; dt_phys_base = round_down(dt_phys, PAGE_SIZE); offset = dt_phys % PAGE_SIZE; dt_virt = (void *)dt_virt_base + offset; /* map the first chunk so we can read the size from the header */ create_mapping_noalloc(dt_phys_base, dt_virt_base, PAGE_SIZE, prot); if (fdt_magic(dt_virt) != FDT_MAGIC) return NULL; *size = fdt_totalsize(dt_virt); if (*size > MAX_FDT_SIZE) return NULL; if (offset + *size > PAGE_SIZE) { create_mapping_noalloc(dt_phys_base, dt_virt_base, offset + *size, prot); } return dt_virt; } |
| 4 4 4 4 4 3 4 4 2 2 4 4 4 4 4 11 21 21 95 44 56 55 56 56 8 8 2 8 2 1 1 1 1 31 79 70 70 70 70 25 5 4 2 2 1 57 56 2 1 56 57 57 57 57 53 53 53 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/irqchip/arm-gic-v3.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/kstrtox.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <linux/string_choices.h> #include <kvm/arm_vgic.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_asm.h> #include "vgic.h" static bool group0_trap; static bool group1_trap; static bool common_trap; static bool dir_trap; static bool gicv4_enable; void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; cpuif->vgic_hcr |= ICH_HCR_UIE; } static bool lr_signals_eoi_mi(u64 lr_val) { return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) && !(lr_val & ICH_LR_HW); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; int lr; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); cpuif->vgic_hcr &= ~ICH_HCR_UIE; for (lr = 0; lr < cpuif->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; u32 intid, cpuid; struct vgic_irq *irq; bool is_v2_sgi = false; bool deactivated; cpuid = val & GICH_LR_PHYSID_CPUID; cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; if (model == KVM_DEV_TYPE_ARM_VGIC_V3) { intid = val & ICH_LR_VIRTUAL_ID_MASK; } else { intid = val & GICH_LR_VIRTUALID; is_v2_sgi = vgic_irq_is_sgi(intid); } /* Notify fds when the guest EOI'ed a level-triggered IRQ */ if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) kvm_notify_acked_irq(vcpu->kvm, 0, intid - VGIC_NR_PRIVATE_IRQS); irq = vgic_get_vcpu_irq(vcpu, intid); if (!irq) /* An LPI could have been unmapped. */ continue; raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit, note deactivation */ deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT); irq->active = !!(val & ICH_LR_ACTIVE_BIT); if (irq->active && is_v2_sgi) irq->active_source = cpuid; /* Edge is the only case where we preserve the pending bit */ if (irq->config == VGIC_CONFIG_EDGE && (val & ICH_LR_PENDING_BIT)) { irq->pending_latch = true; if (is_v2_sgi) irq->source |= (1 << cpuid); } /* * Clear soft pending state when level irqs have been acked. */ if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) irq->pending_latch = false; /* Handle resampling for mapped interrupts if required */ vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT); raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } cpuif->used_lrs = 0; } /* Requires the irq to be locked already */ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) { u32 model = vcpu->kvm->arch.vgic.vgic_model; u64 val = irq->intid; bool allow_pending = true, is_v2_sgi; is_v2_sgi = (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2); if (irq->active) { val |= ICH_LR_ACTIVE_BIT; if (is_v2_sgi) val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; if (vgic_irq_is_multi_sgi(irq)) { allow_pending = false; val |= ICH_LR_EOI; } } if (irq->hw && !vgic_irq_needs_resampling(irq)) { val |= ICH_LR_HW; val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT; /* * Never set pending+active on a HW interrupt, as the * pending state is kept at the physical distributor * level. */ if (irq->active) allow_pending = false; } else { if (irq->config == VGIC_CONFIG_LEVEL) { val |= ICH_LR_EOI; /* * Software resampling doesn't work very well * if we allow P+A, so let's not do that. */ if (irq->active) allow_pending = false; } } if (allow_pending && irq_is_pending(irq)) { val |= ICH_LR_PENDING_BIT; if (irq->config == VGIC_CONFIG_EDGE) irq->pending_latch = false; if (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2) { u32 src = ffs(irq->source); if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", irq->intid)) return; val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; irq->source &= ~(1 << (src - 1)); if (irq->source) { irq->pending_latch = true; val |= ICH_LR_EOI; } } } /* * Level-triggered mapped IRQs are special because we only observe * rising edges as input to the VGIC. We therefore lower the line * level here, so that we can take new virtual IRQs. See * vgic_v3_fold_lr_state for more info. */ if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) irq->line_level = false; if (irq->group) val |= ICH_LR_GROUP; val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT; vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val; } void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr) { vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0; } void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) & ICH_VMCR_ACK_CTL_MASK; vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) & ICH_VMCR_FIQ_EN_MASK; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcr = ICH_VMCR_FIQ_EN_MASK; } vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK; vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK; vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK; vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK; cpu_if->vgic_vmcr = vmcr; } void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; vmcr = cpu_if->vgic_vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >> ICH_VMCR_ACK_CTL_SHIFT; vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >> ICH_VMCR_FIQ_EN_SHIFT; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcrp->fiqen = 1; vmcrp->ackctl = 0; } vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT; vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; vmcrp->grpen0 = (vmcr & ICH_VMCR_ENG0_MASK) >> ICH_VMCR_ENG0_SHIFT; vmcrp->grpen1 = (vmcr & ICH_VMCR_ENG1_MASK) >> ICH_VMCR_ENG1_SHIFT; } #define INITIAL_PENDBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)) void vgic_v3_enable(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; /* * By forcing VMCR to zero, the GIC will restore the binary * points to their reset values. Anything else resets to zero * anyway. */ vgic_v3->vgic_vmcr = 0; /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; } vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_ID_BITS_MASK) >> ICH_VTR_ID_BITS_SHIFT; vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_PRI_BITS_MASK) >> ICH_VTR_PRI_BITS_SHIFT) + 1; /* Get the show on the road... */ vgic_v3->vgic_hcr = ICH_HCR_EN; } void vcpu_set_ich_hcr(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; /* Hide GICv3 sysreg if necessary */ if (!kvm_has_gicv3(vcpu->kvm)) { vgic_v3->vgic_hcr |= ICH_HCR_TALL0 | ICH_HCR_TALL1 | ICH_HCR_TC; return; } if (group0_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL0; if (group1_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL1; if (common_trap) vgic_v3->vgic_hcr |= ICH_HCR_TC; if (dir_trap) vgic_v3->vgic_hcr |= ICH_HCR_TDIR; } int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) { struct kvm_vcpu *vcpu; int byte_offset, bit_nr; gpa_t pendbase, ptr; bool status; u8 val; int ret; unsigned long flags; retry: vcpu = irq->target_vcpu; if (!vcpu) return 0; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; status = val & (1 << bit_nr); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu != vcpu) { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); goto retry; } irq->pending_latch = status; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } return 0; } /* * The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ static void unmap_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); } static void map_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), dist->its_vm.vpes[i]->irq)); } /* * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; gpa_t last_ptr = ~(gpa_t)0; bool vlpi_avail = false; unsigned long index; int ret = 0; u8 val; if (unlikely(!vgic_initialized(kvm))) return -ENXIO; /* * A preparation for getting any VLPI states. * The above vgic initialized check also ensures that the allocation * and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { unmap_all_vpes(kvm); vlpi_avail = true; } xa_for_each(&dist->lpi_xa, index, irq) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; bool is_pending; bool stored; vcpu = irq->target_vcpu; if (!vcpu) continue; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; last_ptr = ptr; } stored = val & (1U << bit_nr); is_pending = irq->pending_latch; if (irq->hw && vlpi_avail) vgic_v4_get_vlpi_state(irq, &is_pending); if (stored == is_pending) continue; if (is_pending) val |= 1 << bit_nr; else val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } out: if (vlpi_avail) map_all_vpes(kvm); return ret; } /** * vgic_v3_rdist_overlap - check if a region overlaps with any * existing redistributor region * * @kvm: kvm handle * @base: base of the region * @size: size of region * * Return: true if there is an overlap */ bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, &d->rd_regions, list) { if ((base + size > rdreg->base) && (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) return true; } return false; } /* * Check for overlapping regions and for regions crossing the end of memory * for base addresses which have already been set. */ bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; list_for_each_entry(rdreg, &d->rd_regions, list) { size_t sz = vgic_v3_rd_region_size(kvm, rdreg); if (vgic_check_iorange(kvm, VGIC_ADDR_UNDEF, rdreg->base, SZ_64K, sz)) return false; } if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) return true; return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, KVM_VGIC_V3_DIST_SIZE); } /** * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one * which has free space to put a new rdist region. * * @rd_regions: redistributor region list head * * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). * Stride between redistributors is 0 and regions are filled in the index order. * * Return: the redist region handle, if any, that has space to map a new rdist * region. */ struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) { struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (!vgic_v3_redist_region_full(rdreg)) return rdreg; } return NULL; } struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index) { struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (rdreg->index == index) return rdreg; } return NULL; } int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_debug("Need to set vgic distributor addresses first\n"); return -ENXIO; } if (!vgic_v3_check_base(kvm)) { kvm_debug("VGIC redist and dist frames overlap\n"); return -EINVAL; } /* * For a VGICv3 we require the userland to explicitly initialize * the VGIC before we need to use it. */ if (!vgic_initialized(kvm)) { return -EBUSY; } if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); static int __init early_group0_trap_cfg(char *buf) { return kstrtobool(buf, &group0_trap); } early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); static int __init early_group1_trap_cfg(char *buf) { return kstrtobool(buf, &group1_trap); } early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); static int __init early_common_trap_cfg(char *buf) { return kstrtobool(buf, &common_trap); } early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); static int __init early_gicv4_enable(char *buf) { return kstrtobool(buf, &gicv4_enable); } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; static bool vgic_v3_broken_seis(void) { return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && is_midr_in_range_list(read_cpuid_id(), broken_seis)); } /** * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller * @info: pointer to the GIC description * * Returns 0 if the VGICv3 has been probed successfully, returns an error code * otherwise */ int vgic_v3_probe(const struct gic_kvm_info *info) { u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config); bool has_v2; int ret; has_v2 = ich_vtr_el2 >> 63; ich_vtr_el2 = (u32)ich_vtr_el2; /* * The ListRegs field is 5 bits, but there is an architectural * maximum of 16 list registers. Just ignore bit 4... */ kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1; kvm_vgic_global_state.can_emulate_gicv2 = false; kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2; /* GICv4 support? */ if (info->has_v4) { kvm_vgic_global_state.has_gicv4 = gicv4_enable; kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; kvm_info("GICv4%s support %s\n", kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", str_enabled_disabled(gicv4_enable)); } kvm_vgic_global_state.vcpu_base = 0; if (!info->vcpu.start) { kvm_info("GICv3: no GICV resource entry\n"); } else if (!has_v2) { pr_warn(FW_BUG "CPU interface incapable of MMIO access\n"); } else if (!PAGE_ALIGNED(info->vcpu.start)) { pr_warn("GICV physical address 0x%llx not page aligned\n", (unsigned long long)info->vcpu.start); } else if (kvm_get_mode() != KVM_MODE_PROTECTED) { kvm_vgic_global_state.vcpu_base = info->vcpu.start; kvm_vgic_global_state.can_emulate_gicv2 = true; ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); if (ret) { kvm_err("Cannot register GICv2 KVM device.\n"); return ret; } kvm_info("vgic-v2@%llx\n", info->vcpu.start); } ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) { kvm_err("Cannot register GICv3 KVM device.\n"); kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2); return ret; } if (kvm_vgic_global_state.vcpu_base == 0) kvm_info("disabling GICv2 emulation\n"); if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_30115)) { group0_trap = true; group1_trap = true; } if (vgic_v3_broken_seis()) { kvm_info("GICv3 with broken locally generated SEI\n"); kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; group0_trap = true; group1_trap = true; if (ich_vtr_el2 & ICH_VTR_TDS_MASK) dir_trap = true; else common_trap = true; } if (group0_trap || group1_trap || common_trap | dir_trap) { kvm_info("GICv3 sysreg trapping enabled ([%s%s%s%s], reduced performance)\n", group0_trap ? "G0" : "", group1_trap ? "G1" : "", common_trap ? "C" : "", dir_trap ? "D" : ""); static_branch_enable(&vgic_v3_cpuif_trap); } kvm_vgic_global_state.vctrl_base = NULL; kvm_vgic_global_state.type = VGIC_V3; kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; return 0; } void vgic_v3_load(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; if (likely(!is_protected_kvm_enabled())) kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); if (has_vhe()) __vgic_v3_activate_traps(cpu_if); WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; if (likely(!is_protected_kvm_enabled())) kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); WARN_ON(vgic_v4_put(vcpu)); if (has_vhe()) __vgic_v3_deactivate_traps(cpu_if); } |
| 193 192 194 194 194 194 155 154 206 207 207 207 207 207 24 193 194 194 194 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_irq(&wb->work_lock); } /* * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just * set up a timer which wakes the bdi thread up later. * * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. * * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ static void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->dwork, timeout); spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(work); spin_unlock_irq(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ /* * Maximum inodes per isw. A specific value has been chosen to make * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. */ #define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ / sizeof(struct inode *)) static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct folio *folio) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (folio) { memcg_css = mem_cgroup_css_from_folio(folio); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } /** * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list * @inode: inode of interest with i_lock held * @wb: target bdi_writeback * * Remove the inode from wb's io lists and if necessarily put onto b_attached * list. Only inodes attached to cgwb's are kept on this list. */ static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct rcu_work work; /* * Multiple inodes can be switched at once. The switching procedure * consists of two parts, separated by a RCU grace period. To make * sure that the second part is executed for each inode gone through * the first part, all inode pointers are placed into a NULL-terminated * array embedded into struct inode_switch_wbs_context. Otherwise * an inode could be left in a non-consistent state. */ struct bdi_writeback *new_wb; struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static bool inode_do_switch_wbs(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb) { struct address_space *mapping = inode->i_mapping; XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; bool switched = false; spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction * path owns the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to * folios actually under writeback. */ xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (folio_test_dirty(folio)) { long nr = folio_nr_pages(folio); wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr); wb_stat_mod(new_wb, WB_RECLAIMABLE, nr); } } xas_set(&xas, 0); xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { long nr = folio_nr_pages(folio); WARN_ON_ONCE(!folio_test_writeback(folio)); wb_stat_mod(old_wb, WB_WRITEBACK, -nr); wb_stat_mod(new_wb, WB_WRITEBACK, nr); } if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { atomic_dec(&old_wb->writeback_inodes); atomic_inc(&new_wb->writeback_inodes); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, * the specific list @inode was on is ignored and the @inode is put on * ->b_dirty which is always correct including from ->b_dirty_time. * The transfer preserves @inode->dirtied_when ordering. If the @inode * was clean, it means it was on the b_attached list, so move it onto * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { inode->i_wb = new_wb; if (inode->i_state & I_DIRTY_ALL) { struct inode *pos; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode_cgwb_move_to_attached(inode, new_wb); } } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); return switched; } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; struct bdi_writeback *new_wb = isw->new_wb; unsigned long nr_switched = 0; struct inode **inodep; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } for (inodep = isw->inodes; *inodep; inodep++) { WARN_ON_ONCE((*inodep)->i_wb != old_wb); if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) nr_switched++; } spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (nr_switched) { wb_wakeup(new_wb); wb_put_many(old_wb, nr_switched); } for (inodep = isw->inodes; *inodep; inodep++) iput(*inodep); wb_put(new_wb); kfree(isw); atomic_dec(&isw_nr_in_flight); } static bool inode_prepare_wbs_switch(struct inode *inode, struct bdi_writeback *new_wb) { /* * Paired with smp_mb() in cgroup_writeback_umount(). * isw_nr_in_flight must be increased before checking SB_ACTIVE and * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 * in cgroup_writeback_umount() and the isw_wq will be not flushed. */ smp_mb(); if (IS_DAX(inode)) return false; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || inode_to_wb(inode) == new_wb) { spin_unlock(&inode->i_lock); return false; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); return true; } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(struct_size(isw, inodes, 2), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, struct list_head *list, int *nr) { struct inode *inode; list_for_each_entry(inode, list, i_io_list) { if (!inode_prepare_wbs_switch(inode, isw->new_wb)) continue; isw->inodes[*nr] = inode; (*nr)++; if (*nr >= WB_MAX_INODES_PER_ISW - 1) return true; } return false; } /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb * * Switch all inodes attached to @wb to a nearest living ancestor's wb in order * to eventually release the dying @wb. Returns %true if not all inodes were * switched and the function has to be restarted. */ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; int nr; bool restart = false; isw = kzalloc(struct_size(isw, inodes, WB_MAX_INODES_PER_ISW), GFP_KERNEL); if (!isw) return restart; atomic_inc(&isw_nr_in_flight); for (memcg_css = wb->memcg_css->parent; memcg_css; memcg_css = memcg_css->parent) { isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); if (isw->new_wb) break; } if (unlikely(!isw->new_wb)) isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ nr = 0; spin_lock(&wb->list_lock); /* * In addition to the inodes that have completed writeback, also switch * cgwbs for those inodes only with dirty timestamps. Otherwise, those * inodes won't be written back for a long time when lazytime is * enabled, and thus pinning the dying cgwbs. It won't break the * bandwidth restrictions, as writeback of inode metadata is not * accounted for. */ restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); if (!restart) restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ if (nr == 0) { atomic_dec(&isw_nr_in_flight); wb_put(isw->new_wb); kfree(isw); return restart; } /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return restart; } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } /** * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite * @wbc: writeback_control of interest * @inode: target inode * * This function is to be used by __filemap_fdatawrite_range(), which is an * alternative entry point into writeback code, and first ensures @inode is * associated with a bdi_writeback and attaches it to @wbc. */ void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { spin_lock(&inode->i_lock); inode_attach_wb(inode, NULL); wbc_attach_and_unlock_inode(wbc, inode); } EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @folio: folio being written out * @bytes: number of bytes being written out * * @bytes from @folio are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_folio(folio); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; unsigned long dirty; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * The caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. * * BTW the memcg stats are flushed periodically and this is best-effort * estimation, so some potential error is ok. */ dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); dirty = dirty * 10 / 8; /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * @sb: target super_block * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(struct super_block *sb) { if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) return; /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). */ smp_mb(); if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { spin_unlock(&inode->i_lock); } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; /* * When the inode is being freed just don't bother with dirty list * tracking. Flush worker will ignore this inode anyway and it will * trigger assertions in inode_io_list_move_locked(). */ if (inode->i_state & I_FREEING) { list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); return; } if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue', * we don't take inode->i_lock here because it is just a pointless overhead. * Inode is already marked as I_SYNC_QUEUED so writeback list handling is * fully under our control. */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ void inode_wait_for_writeback(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; assert_spin_locked(&inode->i_lock); if (!(inode->i_state & I_SYNC)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ if (!(inode->i_state & I_SYNC)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; bool sleep; assert_spin_locked(&inode->i_lock); wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ sleep = !!(inode->i_state & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wq_head, &wqe.wq_entry); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc, unsigned long dirtied_before) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * Writeback is not making progress due to locked buffers. * Skip this inode for now. Although having skipped pages * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ if (inode->i_state & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0 && !inode_dirtied_after(inode, dirtied_before)) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); } } /* * Write out an inode and its dirty pages (or some of its dirty pages, depending * on @wbc->nr_to_write), and clear the relevant dirty flags from i_state. * * This doesn't remove the inode from the writeback list it is on, except * potentially to move it from b_dirty_time to b_dirty due to timestamp * expiration. The caller is otherwise responsible for writeback list handling. * * The caller is also responsible for setting the I_SYNC flag beforehand and * calling inode_sync_complete() to clear it afterwards. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Get and clear the dirty flags from i_state. This needs to be done * after calling writepages because some filesystems may redirty the * inode during writepages due to delalloc. It also needs to be done * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { if (!(inode->i_state & I_DIRTY_PAGES)) { inode->i_state &= ~I_PINNING_NETFS_WB; wbc->unpinned_netfs_wb = true; dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ } } spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } wbc->unpinned_netfs_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty data and metadata on-demand, i.e. separately from * the regular batched writeback done by the flusher threads in * writeback_sb_inodes(). @wbc controls various aspects of the write, such as * whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE). * * To prevent the inode from going away, either the caller must have a reference * to the inode, or the inode must have I_WILL_FREE or I_FREEING set. */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we * must wait for the existing writeback to complete, then do * writeback again if there's anything left. */ if (wbc->sync_mode != WB_SYNC_ALL) goto out; inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * * For data-integrity syncs we also need to check whether any pages are * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If * there are any such pages, we'll need to wait for them. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If the inode is freeing, its i_io_list shoudn't be updated * as it can be finally deleted at this moment. */ if (!(inode->i_state & I_FREEING)) { /* * If the inode is now fully clean, then it can be safely * removed from its writeback list (if any). Otherwise the * flusher threads are responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); else if (!(inode->i_state & I_SYNC_QUEUED)) { if ((inode->i_state & I_DIRTY)) redirty_tail_locked(inode, wb); else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); } } } spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ unsigned long dirtied_before = jiffies; if (work->for_kupdate) dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ requeue_io(inode, wb); spin_unlock(&inode->i_lock); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current->plug, false); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!super_trylock_shared(sb)) { /* * super_trylock_shared() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; bool queued = false; blk_start_plug(&plug); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; spin_lock(&wb->list_lock); trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) { /* * Kupdate and background works are special and we want * to include all inodes that need writing. Livelock * avoidance is handled by these works yielding to any * other work so we are safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; queue_io(wb, work, dirtied_before); queued = true; } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) { spin_unlock(&wb->list_lock); break; } /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); } blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_irq(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); } /* * Start writeback of all dirty pages on this bdi. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ blk_flush_plug(current->plug, true); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function to mark an inode dirty * * @inode: inode to mark * @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of * multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined * with I_DIRTY_PAGES. * * Mark an inode as dirty. We notify the filesystem, then update the inode's * dirty flags. Then, if needed we add the inode to the appropriate dirty list. * * Most callers should use mark_inode_dirty() or mark_inode_dirty_sync() * instead of calling this directly. * * CAREFUL! We only add the inode to the dirty list if it is hashed or if it * refers to a blockdev. Unhashed inodes will never be added to the dirty list * even if they are later hashed, as they will have been marked dirty already. * * In short, ensure you hash any inodes _before_ you start marking them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime = 0; struct bdi_writeback *wb = NULL; trace_writeback_mark_inode_dirty(inode, flags); if (flags & I_DIRTY_INODE) { /* * Inode timestamp update will piggback on this dirtying. * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); if (inode->i_state & I_DIRTY_TIME) { inode->i_state &= ~I_DIRTY_TIME; flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); } /* * Notify the filesystem about the inode being dirtied, so that * (if needed) it can update on-disk fields and journal the * inode. This is only needed when the inode itself is being * dirtied now. I.e. it's only needed for I_DIRTY_INODE, not * for just I_DIRTY_PAGES or I_DIRTY_TIME. */ trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags); /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ flags &= ~I_DIRTY_TIME; } else { /* * Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing. * (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME * in one call to __mark_inode_dirty().) */ dirtytime = flags & I_DIRTY_TIME; WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME); } /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if ((inode->i_state & flags) == flags) return; spin_lock(&inode->i_lock); if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); inode->i_state |= flags; /* * Grab inode's wb early because it requires dropping i_lock and we * need to make sure following checks happen atomically with dirty * list handling so that we don't move inodes under flush worker's * hands. */ if (!was_dirty) { wb = locked_inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); } /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock; } if (inode->i_state & I_FREEING) goto out_unlock; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct list_head *dirty_list; bool wakeup_bdi = false; inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock: if (wb) spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 399 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/mmu_context.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_CONTEXT_H #define __ASM_MMU_CONTEXT_H #ifndef __ASSEMBLY__ #include <linux/compiler.h> #include <linux/sched.h> #include <linux/sched/hotplug.h> #include <linux/mm_types.h> #include <linux/pgtable.h> #include <linux/pkeys.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/daifflags.h> #include <asm/gcs.h> #include <asm/proc-fns.h> #include <asm/cputype.h> #include <asm/sysreg.h> #include <asm/tlbflush.h> extern bool rodata_full; static inline void contextidr_thread_switch(struct task_struct *next) { if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) return; write_sysreg(task_pid_nr(next), contextidr_el1); isb(); } /* * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0. */ static inline void cpu_set_reserved_ttbr0_nosync(void) { unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); write_sysreg(ttbr, ttbr0_el1); } static inline void cpu_set_reserved_ttbr0(void) { cpu_set_reserved_ttbr0_nosync(); isb(); } void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm); static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) { BUG_ON(pgd == swapper_pg_dir); cpu_do_switch_mm(virt_to_phys(pgd),mm); } /* * TCR.T0SZ value to use when the ID map is active. */ #define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. */ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz) { unsigned long tcr = read_sysreg(tcr_el1); if ((tcr & TCR_T0SZ_MASK) == t0sz) return; tcr &= ~TCR_T0SZ_MASK; tcr |= t0sz; write_sysreg(tcr, tcr_el1); isb(); } #define cpu_set_default_tcr_t0sz() __cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual)) #define cpu_set_idmap_tcr_t0sz() __cpu_set_tcr_t0sz(idmap_t0sz) /* * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm. * * The idmap lives in the same VA range as userspace, but uses global entries * and may use a different TCR_EL1.T0SZ. To avoid issues resulting from * speculative TLB fetches, we must temporarily install the reserved page * tables while we invalidate the TLBs and set up the correct TCR_EL1.T0SZ. * * If current is a not a user task, the mm covers the TTBR1_EL1 page tables, * which should not be installed in TTBR0_EL1. In this case we can leave the * reserved page tables in place. */ static inline void cpu_uninstall_idmap(void) { struct mm_struct *mm = current->active_mm; cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); if (mm != &init_mm && !system_uses_ttbr0_pan()) cpu_switch_mm(mm->pgd, mm); } static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* * Load our new page tables. A strict BBM approach requires that we ensure that * TLBs are free of any entries that may overlap with the global mappings we are * about to install. * * For a real hibernate/resume/kexec cycle TTBR0 currently points to a zero * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI runtime * services), while for a userspace-driven test_resume cycle it points to * userspace page tables (and we must point it at a zero page ourselves). * * We change T0SZ as part of installing the idmap. This is undone by * cpu_uninstall_idmap() in __cpu_suspend_exit(). */ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); __cpu_set_tcr_t0sz(t0sz); /* avoid cpu_switch_mm() and its SW-PAN and CNP interactions */ write_sysreg(ttbr0, ttbr0_el1); isb(); } void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); __cpu_replace_ttbr1(pgdp, false); } /* * It would be nice to return ASIDs back to the allocator, but unfortunately * that introduces a race with a generation rollover where we could erroneously * free an ASID allocated in a future generation. We could workaround this by * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap), * but we'd then need to make sure that we didn't dirty any TLBs afterwards. * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you * take CPU migration into account. */ void check_and_switch_context(struct mm_struct *mm); #define init_new_context(tsk, mm) init_new_context(tsk, mm) static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { atomic64_set(&mm->context.id, 0); refcount_set(&mm->context.pinned, 0); /* pkey 0 is the default, so always reserve it. */ mm->context.pkey_allocation_map = BIT(0); return 0; } static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) { } static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } #ifdef CONFIG_ARM64_SW_TTBR0_PAN static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { u64 ttbr; if (!system_uses_ttbr0_pan()) return; if (mm == &init_mm) ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); else ttbr = phys_to_ttbr(virt_to_phys(mm->pgd)) | ASID(mm) << 48; WRITE_ONCE(task_thread_info(tsk)->ttbr0, ttbr); } #else static inline void update_saved_ttbr0(struct task_struct *tsk, struct mm_struct *mm) { } #endif #define enter_lazy_tlb enter_lazy_tlb static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { /* * We don't actually care about the ttbr0 mapping, so point it at the * zero page. */ update_saved_ttbr0(tsk, &init_mm); } static inline void __switch_mm(struct mm_struct *next) { /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. */ if (next == &init_mm) { cpu_set_reserved_ttbr0(); return; } check_and_switch_context(next); } static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { if (prev != next) __switch_mm(next); /* * Update the saved TTBR0_EL1 of the scheduled-in task as the previous * value may have not been initialised yet (activate_mm caller) or the * ASID has changed since the last run (following the context switch * of another thread of the same process). */ update_saved_ttbr0(tsk, next); } static inline const struct cpumask * __task_cpu_possible_mask(struct task_struct *p, const struct cpumask *mask) { if (!static_branch_unlikely(&arm64_mismatched_32bit_el0)) return mask; if (!is_compat_thread(task_thread_info(p))) return mask; return system_32bit_el0_cpumask(); } static inline const struct cpumask * task_cpu_possible_mask(struct task_struct *p) { return __task_cpu_possible_mask(p, cpu_possible_mask); } #define task_cpu_possible_mask task_cpu_possible_mask const struct cpumask *task_cpu_fallback_mask(struct task_struct *p); void verify_cpu_asid_bits(void); void post_ttbr_update_workaround(void); unsigned long arm64_mm_context_get(struct mm_struct *mm); void arm64_mm_context_put(struct mm_struct *mm); #define mm_untag_mask mm_untag_mask static inline unsigned long mm_untag_mask(struct mm_struct *mm) { return -1UL >> 8; } /* * Only enforce protection keys on the current process, because there is no * user context to access POR_EL0 for another address space. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { if (!system_supports_poe()) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return por_el0_allows_pkey(vma_pkey(vma), write, execute); } #define deactivate_mm deactivate_mm static inline void deactivate_mm(struct task_struct *tsk, struct mm_struct *mm) { gcs_free(tsk); } #include <asm-generic/mmu_context.h> #endif /* !__ASSEMBLY__ */ #endif /* !__ASM_MMU_CONTEXT_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netprio_cgroup.c Priority Control Group * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/atomic.h> #include <linux/sched/task.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/netprio_cgroup.h> #include <linux/fdtable.h> /* * netprio allocates per-net_device priomap array which is indexed by * css->id. Limiting css ID to 16bits doesn't lose anything. */ #define NETPRIO_ID_MAX USHRT_MAX #define PRIOMAP_MIN_SZ 128 /* * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ static int extend_netdev_table(struct net_device *dev, u32 target_idx) { struct netprio_map *old, *new; size_t new_sz, new_len; /* is the existing priomap large enough? */ old = rtnl_dereference(dev->priomap); if (old && old->priomap_len > target_idx) return 0; /* * Determine the new size. Let's keep it power-of-two. We start * from PRIOMAP_MIN_SZ and double it until it's large enough to * accommodate @target_idx. */ new_sz = PRIOMAP_MIN_SZ; while (true) { new_len = (new_sz - offsetof(struct netprio_map, priomap)) / sizeof(new->priomap[0]); if (new_len > target_idx) break; new_sz *= 2; /* overflowed? */ if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) return -ENOSPC; } /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); if (!new) return -ENOMEM; if (old) memcpy(new->priomap, old->priomap, old->priomap_len * sizeof(old->priomap[0])); new->priomap_len = new_len; /* install the new priomap */ rcu_assign_pointer(dev->priomap, new); if (old) kfree_rcu(old, rcu); return 0; } /** * netprio_prio - return the effective netprio of a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * * Should be called under RCU read or rtnl lock. */ static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; return 0; } /** * netprio_set_prio - set netprio on a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * @prio: prio to set * * Set netprio to @prio on @css-@dev pair. Should be called under rtnl * lock and may fail under memory pressure for non-zero @prio. */ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; int id = css->id; int ret; /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); if (!prio && (!map || map->priomap_len <= id)) return 0; ret = extend_netdev_table(dev, id); if (ret) return ret; map = rtnl_dereference(dev->priomap); map->priomap[id] = prio; return 0; } static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *parent_css = css->parent; struct net_device *dev; int ret = 0; if (css->id > NETPRIO_ID_MAX) return -ENOSPC; if (!parent_css) return 0; rtnl_lock(); /* * Inherit prios from the parent. As all prios are set during * onlining, there is no need to clear them on offline. */ for_each_netdev(&init_net, dev) { u32 prio = netprio_prio(parent_css, dev); ret = netprio_set_prio(css, dev, prio); if (ret) break; } rtnl_unlock(); return ret; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css); } static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { return css->id; } static int read_priomap(struct seq_file *sf, void *v) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) seq_printf(sf, "%s %u\n", dev->name, netprio_prio(seq_css(sf), dev)); rcu_read_unlock(); return 0; } static ssize_t write_priomap(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; int ret; if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) return -ENODEV; rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); rtnl_unlock(); dev_put(dev); return ret ?: nbytes; } static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); return 0; } static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); } } static struct cftype ss_files[] = { { .name = "prioidx", .read_u64 = read_prioidx, }, { .name = "ifpriomap", .seq_show = read_priomap, .write = write_priomap, }, { } /* terminate */ }; struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, .legacy_cftypes = ss_files, }; static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* * Note this is called with rtnl_lock held so we have update side * protection on our rcu assignments */ switch (event) { case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); if (old) kfree_rcu(old, rcu); break; } return NOTIFY_DONE; } static struct notifier_block netprio_device_notifier = { .notifier_call = netprio_device_event }; static int __init init_cgroup_netprio(void) { register_netdevice_notifier(&netprio_device_notifier); return 0; } subsys_initcall(init_cgroup_netprio); |
| 694 5 5 9 358 301 357 537 471 203 538 538 539 292 539 320 82 177 82 47 695 694 695 694 695 103 88 102 50 535 207 31 577 592 314 305 539 539 539 102 102 50 50 54 55 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PGTABLE_H #define __ASM_PGTABLE_H #include <asm/bug.h> #include <asm/proc-fns.h> #include <asm/memory.h> #include <asm/mte.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable-prot.h> #include <asm/tlbflush.h> /* * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) #if VA_BITS == VA_BITS_MIN #define VMALLOC_END (VMEMMAP_START - SZ_8M) #else #define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) #define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) #endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #ifndef __ASSEMBLY__ #include <asm/cmpxchg.h> #include <asm/fixmap.h> #include <asm/por.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <linux/page_table_check.h> #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE /* Set stride and tlb_level in flush_*_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2) #define flush_pud_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page * fault on one CPU which has been handled concurrently by another CPU * does not need to perform additional invalidation. */ #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e)) /* * Macros to convert between a physical address and its placement in a * page table entry, taking care of 52-bit addresses. */ #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else #define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif #define pte_pfn(pte) (__pte_to_phys(pte) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) \ __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pte_none(pte) (!pte_val(pte)) #define __pte_clear(mm, addr, ptep) \ __set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) /* * The following only work if pte_present(). Undefined behaviour otherwise. */ #define pte_present(pte) (pte_valid(pte) || pte_present_invalid(pte)) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_rdonly(pte) (!!(pte_val(pte) & PTE_RDONLY)) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) #define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) #define pte_tagged(pte) ((pte_val(pte) & PTE_ATTRINDX_MASK) == \ PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pte_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pmd_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pte_hw_dirty(pte) (pte_write(pte) && !pte_rdonly(pte)) #define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_present_invalid(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID) /* * Execute-only user mappings do not have the PTE_USER bit set. All valid * kernel mappings have the PTE_UXN bit set. */ #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) /* * Returns true if the pte is valid and has the contiguous bit set. */ #define pte_valid_cont(pte) (pte_valid(pte) && pte_cont(pte)) /* * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. * Note that we can't make any assumptions based on the state of the access * flag, since __ptep_clear_flush_young() elides a DSB when invalidating the * TLB. */ #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) static inline bool por_el0_allows_pkey(u8 pkey, bool write, bool execute) { u64 por; if (!system_supports_poe()) return true; por = read_sysreg_s(SYS_POR_EL0); if (write) return por_elx_allows_write(por, pkey); if (execute) return por_elx_allows_exec(por, pkey); return por_elx_allows_read(por, pkey); } /* * p??_access_permitted() is true for valid user mappings (PTE_USER * bit set, subject to the write permission check). For execute-only * mappings, like PROT_EXEC with EPAN (both PTE_USER and PTE_UXN bits * not set) must return false. PROT_NONE mappings do not have the * PTE_VALID bit set. */ #define pte_access_permitted_no_overlay(pte, write) \ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte))) #define pte_access_permitted(pte, write) \ (pte_access_permitted_no_overlay(pte, write) && \ por_el0_allows_pkey(FIELD_GET(PTE_PO_IDX_MASK, pte_val(pte)), write, false)) #define pmd_access_permitted(pmd, write) \ (pte_access_permitted(pmd_pte(pmd), (write))) #define pud_access_permitted(pud, write) \ (pte_access_permitted(pud_pte(pud), (write))) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) &= ~pgprot_val(prot); return pte; } static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) |= pgprot_val(prot); return pte; } static inline pmd_t clear_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) &= ~pgprot_val(prot); return pmd; } static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) |= pgprot_val(prot); return pmd; } static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkclean(pte_t pte) { pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkdirty(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); if (pte_write(pte)) pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_wrprotect(pte_t pte) { /* * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY * clear), set the PTE_DIRTY bit. */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkyoung(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkspecial(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } static inline pte_t pte_mkcont(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_CONT)); } static inline pte_t pte_mknoncont(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_CONT)); } static inline pte_t pte_mkvalid(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } static inline pte_t pte_mkinvalid(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID)); pte = clear_pte_bit(pte, __pgprot(PTE_VALID)); return pte; } static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); } static inline pte_t pte_mkdevmap(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_UFFD_WP); } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP))); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void __set_pte(pte_t *ptep, pte_t pte) { __set_pte_nosync(ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ if (pte_valid_not_user(pte)) { dsb(ishst); isb(); } } static inline pte_t __ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } extern void __sync_icache_dcache(pte_t pteval); bool pgattr_change_is_safe(pteval_t old, pteval_t new); /* * PTE bits configuration in the presence of hardware Dirty Bit Management * (PTE_WRITE == PTE_DBM): * * Dirty Writable | PTE_RDONLY PTE_WRITE PTE_DIRTY (sw) * 0 0 | 1 0 0 * 0 1 | 1 1 0 * 1 0 | 1 0 1 * 1 1 | 0 1 x * * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via * the page fault mechanism. Checking the dirty status of a pte becomes: * * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, pte_t pte) { pte_t old_pte; if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; old_pte = __ptep_get(ptep); if (!pte_valid(old_pte) || !pte_valid(pte)) return; if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1) return; /* * Check for potential race with hardware updates of the pte * (__ptep_set_access_flags safely changes valid ptes without going * through an invalid entry). */ VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(!pgattr_change_is_safe(pte_val(old_pte), pte_val(pte)), "%s: unsafe attribute change: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); } static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) { if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte); /* * If the PTE would provide user space access to the tags associated * with it then ensure that the MTE tags are synchronised. Although * pte_access_permitted_no_overlay() returns false for exec only * mappings, they don't expose tags (instruction fetches don't check * tags). */ if (system_supports_mte() && pte_access_permitted_no_overlay(pte, false) && !pte_special(pte) && pte_tagged(pte)) mte_sync_tags(pte, nr_pages); } /* * Select all bits except the pfn */ #define pte_pgprot pte_pgprot static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pfn = pte_pfn(pte); return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); } #define pte_advance_pfn pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte)); } static inline void __set_ptes(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); __sync_cache_and_tags(pte, nr); for (;;) { __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_advance_pfn(pte, 1); } } /* * Hugetlb definitions. */ #define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) static inline pte_t pgd_pte(pgd_t pgd) { return __pte(pgd_val(pgd)); } static inline pte_t p4d_pte(p4d_t p4d) { return __pte(p4d_val(p4d)); } static inline pte_t pud_pte(pud_t pud) { return __pte(pud_val(pud)); } static inline pud_t pte_pud(pte_t pte) { return __pud(pte_val(pte)); } static inline pmd_t pud_pmd(pud_t pud) { return __pmd(pud_val(pud)); } static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); } static inline pmd_t pte_pmd(pte_t pte) { return __pmd(pte_val(pte)); } static inline pgprot_t mk_pud_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT); } static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & PTE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } static inline int pte_swp_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_SWP_UFFD_WP); } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { /* * pte_present_invalid() tells us that the pte is invalid from HW * perspective but present from SW perspective, so the fields are to be * interpretted as per the HW layout. The second 2 checks are the unique * encoding that we use for PROT_NONE. It is insufficient to only use * the first check because we share the same encoding scheme with pmds * which support pmd_mkinvalid(), so can be present-invalid without * being PROT_NONE. */ return pte_present_invalid(pte) && !pte_user(pte) && !pte_user_exec(pte); } static inline int pmd_protnone(pmd_t pmd) { return pte_protnone(pmd_pte(pmd)); } #endif #define pmd_present(pmd) pte_present(pmd_pte(pmd)) /* * THP definitions. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) #define pmd_user(pmd) pte_user(pmd_pte(pmd)) #define pmd_user_exec(pmd) pte_user_exec(pmd_pte(pmd)) #define pmd_cont(pmd) pte_cont(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkinvalid(pmd) pte_pmd(pte_mkinvalid(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define pmd_uffd_wp(pmd) pte_uffd_wp(pmd_pte(pmd)) #define pmd_mkuffd_wp(pmd) pte_pmd(pte_mkuffd_wp(pmd_pte(pmd))) #define pmd_clear_uffd_wp(pmd) pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd))) #define pmd_swp_uffd_wp(pmd) pte_swp_uffd_wp(pmd_pte(pmd)) #define pmd_swp_mkuffd_wp(pmd) pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd))) #define pmd_swp_clear_uffd_wp(pmd) \ pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) #endif static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); } #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP #define pmd_special(pte) (!!((pmd_val(pte) & PTE_SPECIAL))) static inline pmd_t pmd_mkspecial(pmd_t pmd) { return set_pmd_bit(pmd, __pgprot(PTE_SPECIAL)); } #endif #define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd)) #define __phys_to_pmd_val(phys) __phys_to_pte_val(phys) #define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT) #define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) #define pud_young(pud) pte_young(pud_pte(pud)) #define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) #define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT)) #define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud)) #define __phys_to_pud_val(phys) __phys_to_pte_val(phys) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP #define pud_special(pte) pte_special(pud_pte(pud)) #define pud_mkspecial(pte) pte_pud(pte_mkspecial(pud_pte(pud))) #endif #define pmd_pgprot pmd_pgprot static inline pgprot_t pmd_pgprot(pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); return __pgprot(pmd_val(pfn_pmd(pfn, __pgprot(0))) ^ pmd_val(pmd)); } #define pud_pgprot pud_pgprot static inline pgprot_t pud_pgprot(pud_t pud) { unsigned long pfn = pud_pfn(pud); return __pgprot(pud_val(pfn_pud(pfn, __pgprot(0))) ^ pud_val(pud)); } static inline void __set_pte_at(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { __sync_cache_and_tags(pte, nr); __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd), PMD_SIZE >> PAGE_SHIFT); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud), PUD_SIZE >> PAGE_SHIFT); } #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) #define __pgd_to_phys(pgd) __pte_to_phys(pgd_pte(pgd)) #define __phys_to_pgd_val(phys) __phys_to_pte_val(phys) #define __pgprot_modify(prot,mask,bits) \ __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) #define pgprot_decrypted(prot) \ __pgprot_modify(prot, PROT_NS_SHARED, PROT_NS_SHARED) #define pgprot_encrypted(prot) \ __pgprot_modify(prot, PROT_NS_SHARED, 0) /* * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define pgprot_device(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) #define pgprot_tagged(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pgprot_mhp pgprot_tagged /* * DMA allocations for non-coherent devices use what the Arm architecture calls * "Normal non-cacheable" memory, which permits speculation, unaligned accesses * and merging of writes. This is different from "Device-nGnR[nE]" memory which * is intended for MMIO and thus forbids speculation, preserves access size, * requires strict alignment and can also force write responses to come from the * endpoint. */ #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, \ PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) #define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) #define pte_leaf_size(pte) (pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 static inline bool pud_sect(pud_t pud) { return false; } static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) #define pud_table(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_TABLE) #endif extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; extern pgd_t swapper_pg_dir[]; extern pgd_t idmap_pg_dir[]; extern pgd_t tramp_pg_dir[]; extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); static inline bool in_swapper_pgdir(void *addr) { return ((unsigned long)addr & PAGE_MASK) == ((unsigned long)swapper_pg_dir & PAGE_MASK); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { #ifdef __PAGETABLE_PMD_FOLDED if (in_swapper_pgdir(pmdp)) { set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd))); return; } #endif /* __PAGETABLE_PMD_FOLDED */ WRITE_ONCE(*pmdp, pmd); if (pmd_valid(pmd)) { dsb(ishst); isb(); } } static inline void pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, __pmd(0)); } static inline phys_addr_t pmd_page_paddr(pmd_t pmd) { return __pmd_to_phys(pmd); } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_page_paddr(pmd)); } /* Find an entry in the third-level page table. */ #define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr)) #define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr)) #define pte_clear_fixmap() clear_fixmap(FIX_PTE) #define pmd_page(pmd) phys_to_page(__pmd_to_phys(pmd)) /* use ONLY for statically allocated translation tables */ #define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr)))) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ #define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot) #if CONFIG_PGTABLE_LEVELS > 2 #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) #ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #else #define pud_leaf(pud) false #endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline bool pgtable_l4_enabled(void); static inline void set_pud(pud_t *pudp, pud_t pud) { if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } WRITE_ONCE(*pudp, pud); if (pud_valid(pud)) { dsb(ishst); isb(); } } static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); } static inline phys_addr_t pud_page_paddr(pud_t pud) { return __pud_to_phys(pud); } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_page_paddr(pud)); } /* Find an entry in the second-level page table. */ #define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) #define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr)) #define pmd_clear_fixmap() clear_fixmap(FIX_PMD) #define pud_page(pud) phys_to_page(__pud_to_phys(pud)) /* use ONLY for statically allocated translation tables */ #define pmd_offset_kimg(dir,addr) ((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr)))) #else #define pud_valid(pud) false #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) #define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL #define pmd_set_fixmap_offset(pudp, addr) ((pmd_t *)pudp) #define pmd_clear_fixmap() #define pmd_offset_kimg(dir,addr) ((pmd_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static __always_inline bool pgtable_l4_enabled(void) { if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) return true; if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_pud_folded(const struct mm_struct *mm) { return !pgtable_l4_enabled(); } #define mm_pud_folded mm_pud_folded #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) #define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & P4D_TABLE_BIT)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { if (in_swapper_pgdir(p4dp)) { set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d))); return; } WRITE_ONCE(*p4dp, p4d); dsb(ishst); isb(); } static inline void p4d_clear(p4d_t *p4dp) { if (pgtable_l4_enabled()) set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) { return __p4d_to_phys(p4d); } #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) { /* Ensure that 'p4dp' indexes a page table according to 'addr' */ VM_BUG_ON(((addr >> P4D_SHIFT) ^ ((u64)p4dp >> 3)) % PTRS_PER_P4D); return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) { BUG_ON(!pgtable_l4_enabled()); return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); } static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); } #define pud_offset_lockless pud_offset_lockless static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) { return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); } #define pud_offset pud_offset static inline pud_t *pud_set_fixmap(unsigned long addr) { if (!pgtable_l4_enabled()) return NULL; return (pud_t *)set_fixmap_offset(FIX_PUD, addr); } static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return pud_set_fixmap(pud_offset_phys(p4dp, addr)); } static inline void pud_clear_fixmap(void) { if (pgtable_l4_enabled()) clear_fixmap(FIX_PUD); } /* use ONLY for statically allocated translation tables */ static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); } #define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else static inline bool pgtable_l4_enabled(void) { return false; } #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ #define pud_set_fixmap(addr) NULL #define pud_set_fixmap_offset(pgdp, addr) ((pud_t *)pgdp) #define pud_clear_fixmap() #define pud_offset_kimg(dir,addr) ((pud_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static __always_inline bool pgtable_l5_enabled(void) { if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_p4d_folded(const struct mm_struct *mm) { return !pgtable_l5_enabled(); } #define mm_p4d_folded mm_p4d_folded #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) #define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & PGD_TABLE_BIT)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { if (in_swapper_pgdir(pgdp)) { set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); return; } WRITE_ONCE(*pgdp, pgd); dsb(ishst); isb(); } static inline void pgd_clear(pgd_t *pgdp) { if (pgtable_l5_enabled()) set_pgd(pgdp, __pgd(0)); } static inline phys_addr_t pgd_page_paddr(pgd_t pgd) { return __pgd_to_phys(pgd); } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) { /* Ensure that 'pgdp' indexes a page table according to 'addr' */ VM_BUG_ON(((addr >> PGDIR_SHIFT) ^ ((u64)pgdp >> 3)) % PTRS_PER_PGD); return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); } static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) { BUG_ON(!pgtable_l5_enabled()); return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); } static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); } #define p4d_offset_lockless p4d_offset_lockless static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) { return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); } static inline p4d_t *p4d_set_fixmap(unsigned long addr) { if (!pgtable_l5_enabled()) return NULL; return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); } static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); } static inline void p4d_clear_fixmap(void) { if (pgtable_l5_enabled()) clear_fixmap(FIX_P4D); } /* use ONLY for statically allocated translation tables */ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); } #define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) #else static inline bool pgtable_l5_enabled(void) { return false; } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) /* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ #define p4d_set_fixmap(addr) NULL #define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) #define p4d_clear_fixmap() #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) static inline p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr) { /* * With runtime folding of the pud, pud_offset_lockless() passes * the 'pgd_t *' we return here to p4d_to_folded_pud(), which * will offset the pointer assuming that it points into * a page-table page. However, the fast GUP path passes us a * pgd_t allocated on the stack and so we must use the original * pointer in 'pgdp' to construct the p4d pointer instead of * using the generic p4d_offset_lockless() implementation. * * Note: reusing the original pointer means that we may * dereference the same (live) page-table entry multiple times. * This is safe because it is still only loaded once in the * context of each level and the CPU guarantees same-address * read-after-read ordering. */ return p4d_offset(pgdp, addr); } #define p4d_offset_lockless p4d_offset_lockless_folded #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) #define pgd_set_fixmap(addr) ((pgd_t *)set_fixmap_offset(FIX_PGD, addr)) #define pgd_clear_fixmap() clear_fixmap(FIX_PGD) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { /* * Normal and Normal-Tagged are two different memory types and indices * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK. */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | PTE_GP | PTE_ATTRINDX_MASK | PTE_PO_IDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); /* * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware * dirtiness again. */ if (pte_sw_dirty(pte)) pte = pte_mkdirty(pte); return pte; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); } extern int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { return __ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return pte_valid(pte) && (pte_user(pte) || pte_user_exec(pte)); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_valid(pmd) && !pmd_table(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_valid(pud) && !pud_table(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif /* * Atomic pte/pmd modifications. */ static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; pte = __ptep_get(ptep); do { old_pte = pte; pte = pte_mkold(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); return pte_young(pte); } static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { int young = __ptep_test_and_clear_young(vma, address, ptep); if (young) { /* * We can elide the trailing DSB here since the worst that can * happen is that a CPU continues to use the young entry in its * TLB and we mistakenly reclaim the associated page. The * window for such an event is bounded by the next * context-switch, which provides a DSB to complete the TLB * invalidation. */ flush_tlb_page_nosync(vma, address); } return young; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { /* Operation applies to PMD table entry only if FEAT_HAFT is enabled */ VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft()); return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); page_table_check_pte_clear(mm, pte); return pte; } static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { __ptep_get_and_clear(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = __ptep_get_and_clear(mm, addr, ptep); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = __ptep_get_and_clear(mm, addr, ptep); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); page_table_check_pmd_clear(mm, pmd); return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep, pte_t pte) { pte_t old_pte; do { old_pte = pte; pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } /* * __ptep_set_wrprotect - mark read-only while transferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { ___ptep_set_wrprotect(mm, address, ptep, __ptep_get(ptep)); } static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, pte_t *ptep, unsigned int nr) { unsigned int i; for (i = 0; i < nr; i++, address += PAGE_SIZE, ptep++) __ptep_set_wrprotect(mm, address, ptep); } static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, cydp_t flags) { pte_t old_pte; do { old_pte = pte; if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { pte = __ptep_get(ptep); if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) __set_pte(ptep, pte_mkclean(pte_mkold(pte))); else __clear_young_dirty_pte(vma, addr, ptep, pte, flags); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { __ptep_set_wrprotect(mm, address, (pte_t *)pmdp); } #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) * bits 2: remember PG_anon_exclusive * bit 3: remember uffd-wp state * bits 6-10: swap type * bit 11: PTE_PRESENT_INVALID (must be zero) * bits 12-61: swap offset */ #define __SWP_TYPE_SHIFT 6 #define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT 12 #define __SWP_OFFSET_BITS 50 #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) #define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK) #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(swp) ((pte_t) { (swp).val }) #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) #define __swp_entry_to_pmd(swp) __pmd((swp).val) #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ /* * Ensure that there are not more swap files than can be encoded in the kernel * PTEs. */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { if (system_supports_mte()) mte_invalidate_tags(type, offset); } static inline void arch_swap_invalidate_area(int type) { if (system_supports_mte()) mte_invalidate_tags_area(type); } #define __HAVE_ARCH_SWAP_RESTORE extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ /* * On AArch64, the cache coherency is handled via the __set_ptes() function. */ static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * We don't do anything here, so there's a very small chance of * us retaking a user fault which we just fixed up. The alternative * is doing a dsb(ishst), but that penalises the fastpath. */ } #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else #define phys_to_ttbr(addr) (addr) #endif /* * On arm64 without hardware Access Flag, copying from user will fail because * the pte is old and cannot be marked young. So we always end up with zeroed * page after fork() + CoW for pfn mappings. We don't always have a * hardware-managed access flag on arm64. */ #define arch_has_hw_pte_young cpu_has_hw_af #ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG #define arch_has_hw_nonleaf_pmd_young system_supports_haft #endif /* * Experimentally, it's cheap to set the access flag in hardware and we * benefit from prefaulting mappings as 'old' to start with. */ #define arch_wants_old_prefaulted_pte cpu_has_hw_af static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION #define ptep_modify_prot_start ptep_modify_prot_start extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define ptep_modify_prot_commit ptep_modify_prot_commit extern void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t new_pte); #ifdef CONFIG_ARM64_CONTPTE /* * The contpte APIs are used to transparently manage the contiguous bit in ptes * where it is possible and makes sense to do so. The PTE_CONT bit is considered * a private implementation detail of the public ptep API (see below). */ extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte); extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep); extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr); extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr); extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * Only bother trying if both the virtual and physical addresses are * aligned and correspond to the last entry in a contig range. The core * code mostly modifies ranges from low to high, so this is the likely * the last modification in the contig range, so a good time to fold. * We can't fold special mappings, because there is no associated folio. */ const unsigned long contmask = CONT_PTES - 1; bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask; if (unlikely(valign)) { bool palign = (pte_pfn(pte) & contmask) == contmask; if (unlikely(palign && pte_valid(pte) && !pte_cont(pte) && !pte_special(pte))) __contpte_try_fold(mm, addr, ptep, pte); } } static __always_inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (unlikely(pte_valid_cont(pte))) __contpte_try_unfold(mm, addr, ptep, pte); } #define pte_batch_hint pte_batch_hint static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { if (!pte_valid_cont(pte)) return 1; return CONT_PTES - (((unsigned long)ptep >> 3) & (CONT_PTES - 1)); } /* * The below functions constitute the public API that arm64 presents to the * core-mm to manipulate PTE entries within their page tables (or at least this * is the subset of the API that arm64 needs to implement). These public * versions will automatically and transparently apply the contiguous bit where * it makes sense to do so. Therefore any users that are contig-aware (e.g. * hugetlb, kernel mapper) should NOT use these APIs, but instead use the * private versions, which are prefixed with double underscore. All of these * APIs except for ptep_get_lockless() are expected to be called with the PTL * held. Although the contiguous bit is considered private to the * implementation, it is deliberately allowed to leak through the getters (e.g. * ptep_get()), back to core code. This is required so that pte_leaf_size() can * provide an accurate size for perf_get_pgtable_size(). But this leakage means * its possible a pte will be passed to a setter with the contiguous bit set, so * we explicitly clear the contiguous bit in those cases to prevent accidentally * setting it in the pgtable. */ #define ptep_get ptep_get static inline pte_t ptep_get(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get(ptep, pte); } #define ptep_get_lockless ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get_lockless(ptep); } static inline void set_pte(pte_t *ptep, pte_t pte) { /* * We don't have the mm or vaddr so cannot unfold contig entries (since * it requires tlb maintenance). set_pte() is not used in core code, so * this should never even be called. Regardless do our best to service * any call and emit a warning if there is any attempt to set a pte on * top of an existing contig range. */ pte_t orig_pte = __ptep_get(ptep); WARN_ON_ONCE(pte_valid_cont(orig_pte)); __set_pte(ptep, pte_mknoncont(pte)); } #define set_ptes set_ptes static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { pte = pte_mknoncont(pte); if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __set_ptes(mm, addr, ptep, pte, 1); contpte_try_fold(mm, addr, ptep, pte); } else { contpte_set_ptes(mm, addr, ptep, pte, nr); } } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __pte_clear(mm, addr, ptep); } #define clear_full_ptes clear_full_ptes static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __clear_full_ptes(mm, addr, ptep, nr, full); } else { contpte_clear_full_ptes(mm, addr, ptep, nr, full); } } #define get_and_clear_full_ptes get_and_clear_full_ptes static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte; if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); pte = __get_and_clear_full_ptes(mm, addr, ptep, nr, full); } else { pte = contpte_get_and_clear_full_ptes(mm, addr, ptep, nr, full); } return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); return __ptep_get_and_clear(mm, addr, ptep); } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_test_and_clear_young(vma, addr, ptep); return contpte_ptep_test_and_clear_young(vma, addr, ptep); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_clear_flush_young(vma, addr, ptep); return contpte_ptep_clear_flush_young(vma, addr, ptep); } #define wrprotect_ptes wrprotect_ptes static __always_inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1)) { /* * Optimization: wrprotect_ptes() can only be called for present * ptes so we only need to check contig bit as condition for * unfold, and we can remove the contig bit from the pte we read * to avoid re-reading. This speeds up fork() which is sensitive * for order-0 folios. Equivalent to contpte_try_unfold(). */ pte_t orig_pte = __ptep_get(ptep); if (unlikely(pte_cont(orig_pte))) { __contpte_try_unfold(mm, addr, ptep, orig_pte); orig_pte = pte_mknoncont(orig_pte); } ___ptep_set_wrprotect(mm, addr, ptep, orig_pte); } else { contpte_wrprotect_ptes(mm, addr, ptep, nr); } } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { wrprotect_ptes(mm, addr, ptep, 1); } #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS static inline int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) { pte_t orig_pte = __ptep_get(ptep); entry = pte_mknoncont(entry); if (likely(!pte_valid_cont(orig_pte))) return __ptep_set_access_flags(vma, addr, ptep, entry, dirty); return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } #define clear_young_dirty_ptes clear_young_dirty_ptes static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); else contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); } #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get #define set_pte __set_pte #define set_ptes __set_ptes #define pte_clear __pte_clear #define clear_full_ptes __clear_full_ptes #define get_and_clear_full_ptes __get_and_clear_full_ptes #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define ptep_get_and_clear __ptep_get_and_clear #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young __ptep_test_and_clear_young #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young __ptep_clear_flush_young #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define ptep_set_wrprotect __ptep_set_wrprotect #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags #define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ |
| 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Neighbour Discovery for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> */ /* * Changes: * * Alexey I. Froloff : RFC6106 (DNSSL) support * Pierre Ynard : export userland ND options * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt * of an RA. * Janos Farkas : kmalloc failure checks * Alexey Kuznetsov : state machine reworked * and moved to net/core. * Pekka Savola : RFC2461 validation * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ #define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/sched.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/route.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/jhash.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); static int ndisc_is_multicast(const void *pkey); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, .is_multicast = ndisc_is_multicast, .allow_add = ndisc_allow_add, .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, .reachable_time = ND_REACHABLE_TIME, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL_GPL(nd_tbl); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; memset(opt + 2, 0, pad); opt += pad; space -= pad; memcpy(opt+2, data, data_len); data_len += 2; opt += data_len; space -= data_len; if (space > 0) memset(opt, 0, space); } EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type); } static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb, void *ha, const u8 *ops_data) { ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT); ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data); } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { int type; if (!cur || !end || cur >= end) return NULL; type = cur->nd_opt_type; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && cur->nd_opt_type != type); return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_6CO || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64; } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { if (!cur || !end || cur >= end) return NULL; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && !ndisc_is_useropt(dev, cur)); return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL; } struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; if (!nd_opt || opt_len < 0 || !ndopts) return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; l = nd_opt->nd_opt_len << 3; if (opt_len < l || l == 0) return NULL; if (ndisc_ops_parse_options(dev, nd_opt, ndopts)) goto next_opt; switch (nd_opt->nd_opt_type) { case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { ND_PRINTK(2, warn, "%s: duplicated ND6 option found: type=%d\n", __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } break; case ND_OPT_PREFIX_INFO: ndopts->nd_opts_pi_end = nd_opt; if (!ndopts->nd_opt_array[nd_opt->nd_opt_type]) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; #ifdef CONFIG_IPV6_ROUTE_INFO case ND_OPT_ROUTE_INFO: ndopts->nd_opts_ri_end = nd_opt; if (!ndopts->nd_opts_ri) ndopts->nd_opts_ri = nd_opt; break; #endif default: unknown = true; } if (ndisc_is_useropt(dev, nd_opt)) { ndopts->nd_useropts_end = nd_opt; if (!ndopts->nd_useropts) ndopts->nd_useropts = nd_opt; } else if (unknown) { /* * Unknown options must be silently ignored, * to accommodate future extension to the * protocol. */ ND_PRINTK(2, notice, "%s: ignored unsupported option; type=%d, len=%d\n", __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len); } next_opt: opt_len -= l; nd_opt = ((void *)nd_opt) + l; } return ndopts; } int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */ case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; case ARPHRD_INFINIBAND: ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; case ARPHRD_IPGRE: return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return ndisc_hashfn(pkey, dev, hash_rnd); } static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) { return neigh_key_eq128(n, pkey); } static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); if (!in6_dev) { return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; ndisc_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); if (dev->flags&IFF_LOOPBACK) neigh->type = RTN_LOCAL; } else if (dev->flags&IFF_POINTOPOINT) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &ndisc_hh_ops; else neigh->ops = &ndisc_generic_ops; if (neigh->nud_state&NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } in6_dev_put(in6_dev); return 0; } static int pndisc_constructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return -EINVAL; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); return 0; } static void pndisc_destructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); } /* called with rtnl held */ static bool ndisc_allow_add(const struct net_device *dev, struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device"); return false; } return true; } static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int len) { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) { ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", __func__); return NULL; } skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ skb_set_owner_w(skb, sk); return skb; } static void ip6_nd_hdr(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int hop_limit, int len) { struct ipv6hdr *hdr; struct inet6_dev *idev; unsigned tclass; rcu_read_lock(); idev = __in6_dev_get(skb->dev); tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; hdr->hop_limit = hop_limit; hdr->saddr = *saddr; hdr->daddr = *daddr; } void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; int err; struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; if (!dst) { struct flowi6 fl6; int oif = skb->dev->ifindex; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); return; } skb_dst_set(skb, dst); } icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, csum_partial(icmp6h, skb->len, 0)); ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); rcu_read_lock(); idev = __in6_dev_get(dst->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } rcu_read_unlock(); } EXPORT_SYMBOL(ndisc_send_skb); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; struct nd_msg *msg; int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; } if (!dev->addr_len) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, .icmp6_router = router, .icmp6_solicited = solicited, .icmp6_override = override, }, .target = *solicited_addr, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_ADVERTISEMENT); ndisc_send_skb(skb, daddr, src_addr); } static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; idev = in6_dev_get(dev); if (!idev) return; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { /* skip tentative addresses until dad completes */ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_OPTIMISTIC)) continue; ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } read_unlock_bh(&idev->lock); in6_dev_put(idev); } struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *saddr, u64 nonce) { int inc_opt = dev->addr_len; struct sk_buff *skb; struct nd_msg *msg; int optlen = 0; if (!saddr) return NULL; if (ipv6_addr_any(saddr)) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return NULL; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, }, .target = *solicit, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) { u8 *opt = skb_put(skb, 8); opt[0] = ND_OPT_NONCE; opt[1] = 8 >> 3; memcpy(opt + 2, &nonce, 6); } return skb; } EXPORT_SYMBOL(ndisc_ns_create); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce) { struct in6_addr addr_buf; struct sk_buff *skb; if (!saddr) { if (ipv6_get_lladdr(dev, &addr_buf, (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC))) return; saddr = &addr_buf; } skb = ndisc_ns_create(dev, solicit, saddr, nonce); if (skb) ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct sk_buff *skb; struct rs_msg *msg; int send_sllao = dev->addr_len; int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * According to section 2.2 of RFC 4429, we must not * send router solicitations with a sllao from * optimistic addresses, but we may send the solicitation * if we don't include the sllao. So here we check * if our address is optimistic, and if so, we * suppress the inclusion of the sllao. */ if (send_sllao) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, dev, 1); if (ifp) { if (ifp->flags & IFA_F_OPTIMISTIC) { send_sllao = 0; } in6_ifa_put(ifp); } else { send_sllao = 0; } } #endif if (send_sllao) optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, }, }; if (send_sllao) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_ROUTER_SOLICITATION); ndisc_send_skb(skb, daddr, saddr); } static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) { /* * "The sender MUST return an ICMP * destination unreachable" */ dst_link_failure(skb); kfree_skb(skb); } /* Called with locked neigh: either read or both */ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) { struct in6_addr *saddr = NULL; struct in6_addr mcaddr; struct net_device *dev = neigh->dev; struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, false, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(READ_ONCE(neigh->nud_state) & NUD_VALID)) { ND_PRINTK(1, dbg, "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } ndisc_send_ns(dev, target, target, saddr, 0); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } static int pndisc_is_router(const void *pkey, struct net_device *dev) { struct pneigh_entry *n; int ret = -1; read_lock_bh(&nd_tbl.lock); n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) ret = !!(n->flags & NTF_ROUTER); read_unlock_bh(&nd_tbl.lock); return ret; } void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts) { neigh_update(neigh, lladdr, new, flags, 0); /* report ndisc ops about neighbour update */ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); } static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); int is_router = -1; SKB_DR(reason); u64 nonce = 0; bool inc; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NS: multicast target address\n"); return reason; } /* * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ if (dad && !ipv6_addr_is_solict_mult(daddr)) { ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return reason; } if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NS: invalid link-layer address length\n"); return reason; } /* RFC2461 7.1.1: * If the IP source address is the unspecified address, * there MUST NOT be source link-layer address option * in the message. */ if (dad) { ND_PRINTK(2, warn, "NS: bad DAD packet (link-layer address option)\n"); return reason; } } if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { if (nonce != 0 && ifp->dad_nonce == nonce) { u8 *np = (u8 *)&nonce; /* Matching nonce if looped back */ ND_PRINTK(2, notice, "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", ifp->idev->dev->name, &ifp->addr, np); goto out; } /* * We are colliding with another node * who is doing DAD * so fail our DAD process */ addrconf_dad_failure(skb, ifp); return reason; } else { /* * This is not a dad solicitation. * If we are an optimistic node, * we should respond. * Otherwise, we should ignore it. */ if (!(ifp->flags & IFA_F_OPTIMISTIC)) goto out; } } idev = ifp->idev; } else { struct net *net = dev_net(dev); /* perhaps an address on the master device */ if (netif_is_l3_slave(dev)) { struct net_device *mdev; mdev = netdev_master_upper_dev_get_rcu(dev); if (mdev) { ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); if (ifp) goto have_ifp; } } idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ return reason; } if (ipv6_chk_acast_addr(net, dev, &msg->target) || (READ_ONCE(idev->cnf.forwarding) && (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc && NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response * by a random time between 0 and * MAX_ANYCAST_DELAY_TIME seconds. * (RFC2461) -- yoshfuji */ struct sk_buff *n = skb_clone(skb, GFP_ATOMIC); if (n) pneigh_enqueue(&nd_tbl, idev->nd_parms, n); goto out; } } else { SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST); goto out; } } if (is_router < 0) is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } if (inc) NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast); else NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast); /* * update / create cache entry * for the source address */ neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) ndisc_update(dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE, NDISC_NEIGHBOUR_SOLICITATION, &ndopts); if (neigh || !dev->header_ops) { ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); reason = SKB_CONSUMED; } out: if (ifp) in6_ifa_put(ifp); else in6_dev_put(idev); return reason; } static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) { struct inet6_dev *idev = __in6_dev_get(dev); switch (READ_ONCE(idev->cnf.accept_untracked_na)) { case 0: /* Don't accept untracked na (absent in neighbor cache) */ return 0; case 1: /* Create new entries from na if currently untracked */ return 1; case 2: /* Create new entries from untracked na only if saddr is in the * same subnet as an address configured on the interface that * received the na */ return !!ipv6_chk_prefix(saddr, dev); default: return 0; } } static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; SKB_DR(reason); u8 new_state; if (skb->len < sizeof(struct nd_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NA: target address is multicast\n"); return reason; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); return reason; } /* For some 802.11 wireless deployments (and possibly other networks), * there will be a NA proxy and unsolicitd packets are attacks * and thus should not be accepted. * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && READ_ONCE(idev->cnf.drop_unsolicited_na)) return reason; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NA: invalid link-layer address length\n"); return reason; } } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { addrconf_dad_failure(skb, ifp); return reason; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) We should not print the error if NA has been received from loopback - it is just our own unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK(1, warn, "NA: %pM advertised our address %pI6c on %s!\n", eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return reason; } neigh = neigh_lookup(&nd_tbl, &msg->target, dev); /* RFC 9131 updates original Neighbour Discovery RFC 4861. * NAs with Target LL Address option without a corresponding * entry in the neighbour cache can now create a STALE neighbour * cache entry on routers. * * entry accept fwding solicited behaviour * ------- ------ ------ --------- ---------------------- * present X X 0 Set state to STALE * present X X 1 Set state to REACHABLE * absent 0 X X Do nothing * absent 1 0 X Do nothing * absent 1 1 X Add a new STALE entry * * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { if (accept_untracked_na(dev, saddr)) { neigh = neigh_create(&nd_tbl, &msg->target, dev); new_state = NUD_STALE; } } if (neigh && !IS_ERR(neigh)) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); if (READ_ONCE(neigh->nud_state) & NUD_FAILED) goto out; /* * Don't update the neighbor cache entry on a proxy NA from * ourselves because either the proxied node is off link or it * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && READ_ONCE(net->ipv6.devconf_all->forwarding) && READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } ndisc_update(dev, neigh, lladdr, new_state, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0), NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts); if ((old_flags & ~neigh->flags) & NTF_ROUTER) { /* * Change: router to host */ rt6_clean_tohost(dev_net(dev), saddr); } reason = SKB_CONSUMED; out: neigh_release(neigh); } return reason; } static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) { struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; SKB_DR(reason); if (skb->len < sizeof(*rs_msg)) return SKB_DROP_REASON_PKT_TOO_SMALL; idev = __in6_dev_get(skb->dev); if (!idev) { ND_PRINTK(1, err, "RS: can't find in6 device\n"); return reason; } /* Don't accept RS if we're not in router mode */ if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* * Don't update NCE if src = ::; * this implies that the source node has no ip address assigned yet. */ if (ipv6_addr_any(saddr)) goto out; /* Parse ND options */ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) goto out; } neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1); if (neigh) { ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER, NDISC_ROUTER_SOLICITATION, &ndopts); neigh_release(neigh); reason = SKB_CONSUMED; } out: return reason; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) { struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra); struct sk_buff *skb; struct nlmsghdr *nlh; struct nduseroptmsg *ndmsg; struct net *net = dev_net(ra->dev); int err; int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + (opt->nd_opt_len << 3)); size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); if (!nlh) { goto nla_put_failure; } ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); err = -EMSGSIZE; errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); bool send_ifinfo_notify = false; struct neighbour *neigh = NULL; struct ndisc_options ndopts; struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; struct fib6_table *table; u32 defrtr_usr_metric; unsigned int pref = 0; __u32 old_if_flags; struct net *net; SKB_DR(reason); int lifetime; int optlen; __u8 *opt = (__u8 *)(ra_msg + 1); optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); ND_PRINTK(2, info, "RA: %s, dev: %s\n", __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return reason; } if (optlen < 0) return SKB_DROP_REASON_PKT_TOO_SMALL; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); return reason; } #endif in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) { ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", skb->dev->name); return reason; } if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #endif if (in6_dev->if_flags & IF_RS_SENT) { /* * flag that an RA was received after an RS was sent * out on this interface. */ in6_dev->if_flags |= IF_RA_RCVD; } /* * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? IF_RA_MANAGED : 0) | (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); goto skip_defrtr; } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); if (lifetime != 0 && lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { ND_PRINTK(2, info, "RA: router lifetime (%ds) is too short: %s\n", lifetime, skb->dev->name); goto skip_defrtr; } /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ net = dev_net(in6_dev->dev); if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); goto skip_defrtr; } #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif /* routes added from RAs do not use nexthop objects */ rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } } /* Set default route metric as specified by user */ defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric; /* delete the route if lifetime is 0 or if metric needs change */ if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) { ip6_del_rt(net, rt, false); rt = NULL; } ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n", rt, lifetime, defrtr_usr_metric, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); if (neigh) neigh_release(neigh); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev, pref, defrtr_usr_metric, lifetime); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", __func__); return reason; } neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6, rt->fib6_nh->fib_nh_dev, NULL, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); fib6_info_release(rt); return reason; } neigh->flags |= NTF_ROUTER; } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) { struct nl_info nlinfo = { .nl_net = net, }; rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); fib6_set_expires(rt, jiffies + (HZ * lifetime)); fib6_add_gc_list(rt); spin_unlock_bh(&table->tb6_lock); } if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && ra_msg->icmph.icmp6_hop_limit) { if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= ra_msg->icmph.icmp6_hop_limit) { WRITE_ONCE(in6_dev->cnf.hop_limit, ra_msg->icmph.icmp6_hop_limit); fib6_metric_set(rt, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } } skip_defrtr: /* * Update Reachable Time and Retrans Timer */ if (in6_dev->nd_parms) { unsigned long rtime = ntohl(ra_msg->retrans_timer); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) { rtime = (rtime*HZ)/1000; if (rtime < HZ/100) rtime = HZ/100; NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) { rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { NEIGH_VAR_SET(in6_dev->nd_parms, BASE_REACHABLE_TIME, rtime); NEIGH_VAR_SET(in6_dev->nd_parms, GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } } } skip_linkparms: /* * Process options. */ if (!neigh) neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr, skb->dev, 1); if (neigh) { u8 *lladdr = NULL; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { ND_PRINTK(2, warn, "RA: invalid link-layer address length\n"); goto out; } } ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER, NDISC_ROUTER_ADVERTISEMENT, &ndopts); reason = SKB_CONSUMED; } if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, accept_ra is false for dev: %s\n", __func__, skb->dev->name); goto out; } #ifdef CONFIG_IPV6_ROUTE_INFO if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); goto skip_routeinfo; } if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { struct route_info *ri = (struct route_info *)p; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT && ri->prefix_len == 0) continue; #endif if (ri->prefix_len == 0 && !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) continue; if (ri->lifetime != 0 && ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) continue; if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); } } skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", __func__, skb->dev->name); goto out; } #endif if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) { addrconf_prefix_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, ndopts.nd_opts_src_lladdr != NULL); } } if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); if (in6_dev->ra_mtu != mtu) { in6_dev->ra_mtu = mtu; send_ifinfo_notify = true; } if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { WRITE_ONCE(in6_dev->cnf.mtu6, mtu); fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } if (ndopts.nd_useropts) { struct nd_opt_hdr *p; for (p = ndopts.nd_useropts; p; p = ndisc_next_useropt(skb->dev, p, ndopts.nd_useropts_end)) { ndisc_ra_useropt(skb, p); } } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: /* Send a notify if RA changed managed/otherconf flags or * timer settings or ra_mtu value */ if (send_ifinfo_notify) inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); fib6_info_release(rt); if (neigh) neigh_release(neigh); return reason; } static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb) { struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); struct ndisc_options ndopts; SKB_DR(reason); u8 *hdr; #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: ND_PRINTK(2, warn, "Redirect: from host or unauthorized router\n"); return reason; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: source address is not link-local\n"); return reason; } if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts)) return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS; if (!ndopts.nd_opts_rh) { ip6_redirect_no_header(skb, dev_net(skb->dev), skb->dev->ifindex); return reason; } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; if (!pskb_pull(skb, hdr - skb_transport_header(skb))) return SKB_DROP_REASON_PKT_TOO_SMALL; return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, struct sk_buff *orig_skb, int rd_len) { u8 *opt = skb_put(skb, rd_len); memset(opt, 0, 8); *(opt++) = ND_OPT_REDIRECT_HDR; *(opt++) = (rd_len >> 3); opt += 6; skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; struct rd_msg *msg; struct in6_addr saddr_buf; struct rt6_info *rt; struct dst_entry *dst; struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) return; } if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: target address is not link-local unicast\n"); return; } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); return; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) { ND_PRINTK(2, warn, "Redirect: destination is not a neighbour\n"); goto release; } rcu_read_lock(); peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr); ret = inet_peer_xrlim_allow(peer, 1*HZ); rcu_read_unlock(); if (!ret) goto release; if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { ND_PRINTK(2, warn, "Redirect: no neigh for target address\n"); goto release; } read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; optlen += ndisc_redirect_opt_addr_space(dev, neigh, ops_data_buf, &ops_data); } else read_unlock_bh(&neigh->lock); neigh_release(neigh); } rd_len = min_t(unsigned int, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, skb->len + 8); rd_len &= ~0x7; optlen += rd_len; buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!buff) goto release; msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, }, .target = *target, .dest = ipv6_hdr(skb)->daddr, }; /* * include target_address option */ if (ha) ndisc_fill_redirect_addr_option(buff, ha, ops_data); /* * build redirect option and copy skb over to the new packet. */ if (rd_len) ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: dst_release(dst); } static void pndisc_redo(struct sk_buff *skb) { enum skb_drop_reason reason = ndisc_recv_ns(skb); kfree_skb_reason(skb, reason); } static int ndisc_is_multicast(const void *pkey) { return ipv6_addr_is_multicast((struct in6_addr *)pkey); } static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && READ_ONCE(idev->cnf.suppress_frag_ndisc)) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } return false; } enum skb_drop_reason ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; SKB_DR(reason); if (ndisc_suppress_frag_ndisc(skb)) return SKB_DROP_REASON_IPV6_NDISC_FRAG; if (skb_linearize(skb)) return SKB_DROP_REASON_NOMEM; msg = (struct nd_msg *)skb_transport_header(skb); __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit); return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT; } if (msg->icmph.icmp6_code != 0) { ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code); return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE; } switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); reason = ndisc_recv_ns(skb); break; case NDISC_NEIGHBOUR_ADVERTISEMENT: reason = ndisc_recv_na(skb); break; case NDISC_ROUTER_SOLICITATION: reason = ndisc_recv_rs(skb); break; case NDISC_ROUTER_ADVERTISEMENT: reason = ndisc_router_discovery(skb); break; case NDISC_REDIRECT: reason = ndisc_redirect_rcv(skb); break; } return reason; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(0, net, false); fallthrough; case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) break; if (READ_ONCE(idev->cnf.ndisc_notify) || READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; case NETDEV_CHANGE: idev = in6_dev_get(dev); if (!idev) evict_nocarrier = true; else { evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); in6_dev_put(idev); } change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strscpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); warned++; } } int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; int ret; if ((strcmp(ctl->procname, "retrans_time") == 0) || (strcmp(ctl->procname, "base_reachable_time") == 0)) ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) idev->nd_parms->reachable_time = neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } return ret; } #endif static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; int err; err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { ND_PRINTK(0, err, "NDISC: Failed to initialize the control socket (err %d)\n", err); return err; } net->ipv6.ndisc_sk = sk; np = inet6_sk(sk); np->hop_limit = 255; /* Do not loopback ndisc messages */ inet6_clear_bit(MC6_LOOP, sk); return 0; } static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, }; int __init ndisc_init(void) { int err; err = register_pernet_subsys(&ndisc_net_ops); if (err) return err; /* * Initialize the neighbour table */ neigh_table_init(NEIGH_ND_TABLE, &nd_tbl); #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: #endif return err; #ifdef CONFIG_SYSCTL out_unregister_pernet: unregister_pernet_subsys(&ndisc_net_ops); goto out; #endif } int __init ndisc_late_init(void) { return register_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_cleanup(void) { #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl); unregister_pernet_subsys(&ndisc_net_ops); } |
| 847 847 168 847 847 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/cleanup.h> #include <linux/kernel.h> #include <linux/bitmap.h> #include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); if (n != -1) cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, * since there is only one valid option. */ if (wrap && n >= 0) return nr_cpumask_bits; return cpumask_first(mask); } #else unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); #endif /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) { unsigned int i; cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_assign_cpu - assign a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer * @bool: the value to assign */ static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick an arbitrary cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 | /* 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. * * The mapcount field must not be used for own purposes. * * 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 swapcache flag set. * 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. */ /* * For head pages of typed folios, the value stored here * allows for determining what this page is used for. The * tail pages of typed folios will not store a type * (page_type == _mapcount == -1). * * See page-flags.h for a list of page types which are currently * stored here. * * Owners of typed folios may reuse the lower 16 bit of the * head page page_type field after setting the page type, * but must reset these 16 bit to -1 before clearing the * page type. */ unsigned int page_type; /* * For pages that are part of non-typed folios for which mappings * are tracked via the RMAP, encodes the number of times this page * is directly referenced by a page table. * * Note that the mapcount is always initialized to -1, so that * transitions both from it and to it can be tracked, using * atomic_inc_and_test() and atomic_add_negative(-1). */ atomic_t _mapcount; }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; #ifdef CONFIG_MEMCG unsigned long memcg_data; #elif defined(CONFIG_SLAB_OBJ_EXT) unsigned long _unused_slab_obj_exts; #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. * @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab. * * 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_MEMCG unsigned long memcg_data; #elif defined(CONFIG_SLAB_OBJ_EXT) unsigned long _unused_slab_obj_exts; #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 gmap shadow pages * (which are not linked into the user page tables) and x86 * pgds. * @_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_share_count: Used for HugeTLB PMD page table share count. * @_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; #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING atomic_t pt_share_count; #endif }; 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))) #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) { atomic_set(&ptdesc->pt_share_count, 0); } static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) { atomic_inc(&ptdesc->pt_share_count); } static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) { atomic_dec(&ptdesc->pt_share_count); } static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) { return atomic_read(&ptdesc->pt_share_count); } #else static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) { } #endif /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) /* * 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; } 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). * * Only explicitly marked struct members may be accessed by RCU readers before * getting a stable reference. */ 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 }; /* * The address space we belong to. * Unstable RCU readers are allowed to read this. */ struct mm_struct *vm_mm; 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. * Unstable RCU readers are allowed to read this. */ 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. */ unsigned int vm_lock_seq; /* Unstable RCU readers are allowed to read this. */ 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; int recent_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; /** * @nr_cpus_allowed: Number of CPUs allowed for mm. * * Number of CPUs allowed in the union of all mm's * threads allowed CPUs. */ unsigned int nr_cpus_allowed; /** * @max_nr_cid: Maximum number of concurrency IDs allocated. * * Track the highest number of concurrency IDs allocated for the * mm. */ atomic_t max_nr_cid; /** * @cpus_allowed_lock: Lock protecting mm cpus_allowed. * * Provide mutual exclusion for mm cpus_allowed and * mm nr_cpus_allowed updates. */ raw_spinlock_t cpus_allowed_lock; #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. * Incremented every time mmap_lock is write-locked/unlocked. * Initialized to 0, therefore odd values indicate mmap_lock * is write-locked and even values that it's released. * * 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. */ seqcount_t 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) && !defined(CONFIG_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. */ atomic_long_t 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; } /* * mm_cpus_allowed: Union of all mm's threads allowed CPUs. */ static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) { unsigned long bitmap = (unsigned long)mm; bitmap += offsetof(struct mm_struct, cpu_bitmap); /* Skip cpu_bitmap */ bitmap += cpumask_size(); return (struct cpumask *)bitmap; } /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm); /* Skip mm_cpus_allowed */ cid_bitmap += cpumask_size(); return (struct cpumask *)cid_bitmap; } static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { 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->recent_cid = MM_CID_UNSET; pcpu_cid->time = 0; } mm->nr_cpus_allowed = p->nr_cpus_allowed; atomic_set(&mm->max_nr_cid, 0); raw_spin_lock_init(&mm->cpus_allowed_lock); cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); cpumask_clear(mm_cidmask(mm)); } static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p) { mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; mm_init_cid(mm, p); 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 2 * cpumask_size(); /* mm_cpus_allowed(), mm_cidmask(). */ } static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { struct cpumask *mm_allowed = mm_cpus_allowed(mm); if (!mm) return; /* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */ raw_spin_lock(&mm->cpus_allowed_lock); cpumask_or(mm_allowed, mm_allowed, cpumask); WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed)); raw_spin_unlock(&mm->cpus_allowed_lock); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; } static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { } #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); void (*close)(const struct vm_special_mapping *sm, struct vm_area_struct *vma); }; enum tlb_flush_reason { TLB_FLUSH_ON_TASK_SWITCH, TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, TLB_REMOTE_WRONG_CPU, 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 */ }; /* mm flags */ /* * The first two bits represent core dump modes for set-user-ID, * the modes are SUID_DUMP_* defined in linux/sched/coredump.h */ #define MMF_DUMPABLE_BITS 2 #define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) /* coredump filter bits */ #define MMF_DUMP_ANON_PRIVATE 2 #define MMF_DUMP_ANON_SHARED 3 #define MMF_DUMP_MAPPED_PRIVATE 4 #define MMF_DUMP_MAPPED_SHARED 5 #define MMF_DUMP_ELF_HEADERS 6 #define MMF_DUMP_HUGETLB_PRIVATE 7 #define MMF_DUMP_HUGETLB_SHARED 8 #define MMF_DUMP_DAX_PRIVATE 9 #define MMF_DUMP_DAX_SHARED 10 #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS #define MMF_DUMP_FILTER_BITS 9 #define MMF_DUMP_FILTER_MASK \ (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) #ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS # define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) #else # define MMF_DUMP_MASK_DEFAULT_ELF 0 #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ #define MMF_VM_HUGEPAGE 17 /* set when mm is available for khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore */ //#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 26 /* mm is shared between processes */ /* * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either * replaced in the future by mm.pinned_vm when it becomes stable, or grow into * a counter on its own. We're aggresive on this bit for now: even if the * pinned pages were unpinned later on, we'll still keep this bit set for the * lifecycle of this mm, just for simplicity. */ #define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ #define MMF_HAS_MDWE 28 #define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) #define MMF_HAS_MDWE_NO_INHERIT 29 #define MMF_VM_MERGE_ANY 30 #define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) #define MMF_TOPDOWN 31 /* mm searches top down by default */ #define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) static inline unsigned long mmf_init_flags(unsigned long flags) { if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) flags &= ~((1UL << MMF_HAS_MDWE) | (1UL << MMF_HAS_MDWE_NO_INHERIT)); return flags & MMF_INIT_MASK; } #endif /* _LINUX_MM_TYPES_H */ |
| 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 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 | // 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. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static void prb_retire_rx_blk_timer_expired(struct timer_list *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { struct vlan_hdr vhdr, *vh; unsigned int header_len; if (!dev) return 0; /* In the SOCK_DGRAM scenario, skb data starts at the network * protocol, which is after the VLAN headers. The outer VLAN * header is at the hard_header_len offset in non-variable * length link layer headers. If it's a VLAN device, the * min_header_len should be used to exclude the VLAN header * size. */ if (dev->min_header_len == dev->hard_header_len) header_len = dev->hard_header_len; else if (is_vlan_dev(dev)) header_len = dev->min_header_len; else return 0; vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) proto = __vlan_get_protocol_offset(skb, proto, skb_mac_offset(skb), NULL); return proto; } static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } static void prb_setup_retire_blk_timer(struct packet_sock *po) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, 0); pkc->retire_blk_timer.expires = jiffies; } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; p1->last_kactive_blk_num = 0; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; else p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size); p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po); prb_open_block(p1, pbd); } /* Do NOT update the last_blk_num first. * Assumes sk_buff_head lock is held. */ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) { mod_timer(&pkc->retire_blk_timer, jiffies + pkc->tov_in_jiffies); pkc->last_kactive_blk_num = pkc->kactive_blk_num; } /* * Timer logic: * 1) We refresh the timer only when we open a block. * By doing this we don't waste cycles refreshing the timer * on packet-by-packet basis. * * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * So, if the user sets the 'tmo' to 10ms then the timer * will never fire while the block is still getting filled * (which is what we want). However, the user could choose * to close a block early and that's fine. * * But when the timer does fire, we check whether or not to refresh it. * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. * */ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) { struct packet_sock *po = from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); if (unlikely(pkc->delete_blk_timer)) goto out; /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { if (!frozen) { if (!BLOCK_NUM_PKTS(pbd)) { /* An empty block. Just refresh the timer. */ goto refresh_timer; } prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); if (!prb_dispatch_next_block(pkc, po)) goto refresh_timer; else goto out; } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (prb_curr_blk_in_use(pbd)) { /* * Ok, user-space is still behind. * So just refresh the timer. */ goto refresh_timer; } else { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); goto out; } } } refresh_timer: _prb_refresh_rx_retire_blk_timer(pkc); out: spin_unlock(&po->sk.sk_receive_queue.lock); } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * Side effect of opening a block: * * 1) prb_queue is thawed. * 2) retire_blk_timer is refreshed. * */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); _prb_refresh_rx_retire_blk_timer(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (po->num && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __dev_remove_pack(&po->prot_hook); __fanout_link(sk, po); } err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, &sockc); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); h.h2->tp_vlan_tpid = ntohs(skb->protocol); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo = 0; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { if (need_wait && skb) { timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } } /* check for additional frames */ continue; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || /* Note: packet_read_pending() might be slow if we have * to call it as it's per_cpu variable, but in fast-path * we already short-circuit the loop with the first * condition, and luckily don't have to go that path * anyway. */ (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, &sockc); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; po = pkt_sk(sk); err = packet_alloc_pending(po); if (err) goto out_sk_free; sock_init_data(sock, sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out_sk_free: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = (sock->type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); if (dev) { aux.tp_vlan_tci = vlan_get_tci(skb, dev); aux.tp_vlan_tpid = ntohs(skb->protocol); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { packet_dev_mc(dev, ml, -1); *mlp = ml->next; kfree(ml); } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: if (optlen < sizeof(req_u.req)) break; ret = copy_from_sockptr(&req_u.req, optval, sizeof(req_u.req)) ? -EINVAL : 0; break; case TPACKET_V3: default: if (optlen < sizeof(req_u.req3)) break; ret = copy_from_sockptr(&req_u.req3, optval, sizeof(req_u.req3)) ? -EINVAL : 0; break; } if (!ret) ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_COPY_THRESH: val = READ_ONCE(pkt_sk(sk)->copy_thresh); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct sock *sk; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; if (was_running) { WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running) { WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> struct fs_struct { int users; spinlock_t lock; seqcount_spinlock_t seq; int umask; int in_exec; struct path root, pwd; } __randomize_layout; extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { spin_lock(&fs->lock); *root = fs->root; path_get(root); spin_unlock(&fs->lock); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { spin_lock(&fs->lock); *pwd = fs->pwd; path_get(pwd); spin_unlock(&fs->lock); } extern bool current_chrooted(void); #endif /* _LINUX_FS_STRUCT_H */ |
| 2 38 631 163 571 59 19 19 15 30 256 159 52 127 127 168 168 103 103 103 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> struct list_lru; /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Three common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] * * xa_limit_16b - [0 - USHRT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) #define xa_limit_16b XA_LIMIT(0, USHRT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; struct list_lru *xa_lru; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL, \ .xa_lru = NULL, \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline int xas_get_order(struct xa_state *xas) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_advance() - Skip over sibling entries. * @xas: XArray operation state. * @index: Index of last sibling entry. * * Move the operation state to refer to the last sibling entry. * This is useful for loops that normally want to see sibling * entries but sometimes want to skip them. Use xas_set() if you * want to move to an index which is not part of this entry. */ static inline void xas_advance(struct xa_state *xas, unsigned long index) { unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; xas->xa_index = index; xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page * cache and swap cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) { xas->xa_lru = lru; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 280 281 280 281 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/dax.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. * * Note that these are only respected if collapse was initiated by khugepaged. */ unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct khugepaged_mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR_RW(max_ptes_none); static ssize_t max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR_RW(max_ptes_swap); static ssize_t max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = KMEM_CACHE(khugepaged_mm_slot, 0); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } static bool hugepage_pmd_enabled(void) { /* * We cover the anon, shmem and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. * Shmem pmd-sized hugepages are also determined by its pmd-size control, * except when the global shmem_huge is set to SHMEM_HUGE_DENY. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_always)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_madvise)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled()) return true; return false; } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we return all * pagetables will be destroyed) until khugepaged has finished * working on the pagetables under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount = folio_mapcount(folio); if (!folio_test_anon(folio) || folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); if (folio_test_private(folio)) expected_refcount++; return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before folio_isolate_lru because the * folio can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static inline int check_pmd_state(pmd_t *pmd) { pmd_t pmde = pmdp_get_lockless(pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; return check_pmd_state(*pmd); } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { /* * Here the ptl is only used to check pte_same() in * do_swap_page(), so readonly version is enough. */ pte = pte_offset_map_ro_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. "False negatives" from * folio_likely_mapped_shared() are not expected to matter * much in practice. */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * @install_pmd: If a huge PMD should be installed * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) goto abort; /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) { spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) { flush_tlb_mm(mm); goto unlock; } } } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); pte_unmap_unlock(start_pte, ptl); if (ptl != pml) spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } unlock: if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool success = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); /* * The lock of new_folio is still held, we will be blocked in * the page fault path, which prevents the pte entries from * being set again. So even though the old empty PTE page may be * concurrently freed and a new PTE page is filled into the pmd * entry, it is still empty and can be removed. * * So here we only need to recheck if the state of pmd entry * still meets our requirements, rather than checking pmd_same() * like elsewhere. */ if (check_pmd_state(pmd) != SCAN_SUCCEED) goto drop_pml; ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); success = true; } if (ptl != pml) spin_unlock(ptl); drop_pml: spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (success) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; mapping_set_update(&xas, mapping); __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto rollback; } } while (1); for (index = start; index < end;) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } } nr_none++; index++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control 2 + nr_pages references to the folio: * - we hold a pin on it; * - nr_pages reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); index += folio_nr_pages(folio); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure i_writecount is up to date and the update to nr_thps * is visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { int i, nr_pages = folio_nr_pages(folio); while (index < folio->index) { clear_highpage(dst); index++; dst++; } for (i = 0; i < nr_pages; i++) { if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 2 + folio_nr_pages(folio)); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); mm = slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (hpage_collapse_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (hugepage_pmd_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; if (!hugepage_pmd_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && !vma_is_anonymous(vma)) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * * Copyright (c) 2002-2017 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/hrtimer.h> #include <linux/list.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> #include <net/sock.h> #include <net/net_namespace.h> /* * To send multiple CAN frame content within TX_SETUP or to filter * CAN messages with multiplex index within RX_SETUP, the number of * different filters is limited to 256 due to the one byte index value. */ #define MAX_NFRAMES 256 /* limit timers to 400 days for sending/timeouts */ #define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60) /* use of last_frames[index].flags */ #define RX_LOCAL 0x10 /* frame was created on the local host */ #define RX_OWN 0x20 /* frame was sent via the socket it was received on */ #define RX_RECV 0x40 /* received data for this element */ #define RX_THR 0x80 /* element not been sent due to throttle feature */ #define BCM_CAN_FLAGS_MASK 0x0F /* to clean private flags after usage */ /* get best masking value for can_rx_register() for a given single can_id */ #define REGMASK(id) ((id & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS("can-proto-2"); #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) /* * easy access to the first 64 bit of can(fd)_frame payload. cp->data is * 64 bit aligned so the offset has to be multiples of 8 which is ensured * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler(). */ static inline u64 get_u64(const struct canfd_frame *cp, int offset) { return *(u64 *)(cp->data + offset); } struct bcm_op { struct list_head list; struct rcu_head rcu; int ifindex; canid_t can_id; u32 flags; unsigned long frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; int cfsiz; u32 count; u32 nframes; u32 currframe; /* void pointers to arrays of struct can[fd]_frame */ void *frames; void *last_frames; struct canfd_frame sframe; struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; }; struct bcm_sock { struct sock sk; int bound; int ifindex; struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; struct proc_dir_entry *bcm_proc_read; char procname [32]; /* inode number in decimal with \0 */ }; static LIST_HEAD(bcm_notifier_list); static DEFINE_SPINLOCK(bcm_notifier_lock); static struct bcm_sock *bcm_busy_notifier; /* Return pointer to store the extra msg flags for bcm_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ static inline unsigned int *bcm_flags(struct sk_buff *skb) { /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); } static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; } static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv) { return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); } /* check limitations for timeval provided by user */ static bool bcm_is_invalid_tv(struct bcm_msg_head *msg_head) { if ((msg_head->ival1.tv_sec < 0) || (msg_head->ival1.tv_sec > BCM_TIMER_SEC_MAX) || (msg_head->ival1.tv_usec < 0) || (msg_head->ival1.tv_usec >= USEC_PER_SEC) || (msg_head->ival2.tv_sec < 0) || (msg_head->ival2.tv_sec > BCM_TIMER_SEC_MAX) || (msg_head->ival2.tv_usec < 0) || (msg_head->ival2.tv_usec >= USEC_PER_SEC)) return true; return false; } #define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU) #define OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) /* * procfs functions */ #if IS_ENABLED(CONFIG_PROC_FS) static char *bcm_proc_getifname(struct net *net, char *result, int ifindex) { struct net_device *dev; if (!ifindex) return "any"; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) strcpy(result, dev->name); else strcpy(result, "???"); rcu_read_unlock(); return result; } static int bcm_proc_show(struct seq_file *m, void *v) { char ifname[IFNAMSIZ]; struct net *net = m->private; struct sock *sk = (struct sock *)pde_data(m->file->f_inode); struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; seq_printf(m, ">>> socket %pK", sk->sk_socket); seq_printf(m, " / sk %pK", sk); seq_printf(m, " / bo %pK", bo); seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs); seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); list_for_each_entry(op, &bo->rx_ops, list) { unsigned long reduction; /* print only active entries & prevent division by zero */ if (!op->frames_abs) continue; seq_printf(m, "rx_op: %03X %-5s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); if (op->flags & CAN_FD_FRAME) seq_printf(m, "(%u)", op->nframes); else seq_printf(m, "[%u]", op->nframes); seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' '); if (op->kt_ival1) seq_printf(m, "timeo=%lld ", (long long)ktime_to_us(op->kt_ival1)); if (op->kt_ival2) seq_printf(m, "thr=%lld ", (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# recv %ld (%ld) => reduction: ", op->frames_filtered, op->frames_abs); reduction = 100 - (op->frames_filtered * 100) / op->frames_abs; seq_printf(m, "%s%ld%%\n", (reduction == 100) ? "near " : "", reduction); } list_for_each_entry(op, &bo->tx_ops, list) { seq_printf(m, "tx_op: %03X %s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); if (op->flags & CAN_FD_FRAME) seq_printf(m, "(%u) ", op->nframes); else seq_printf(m, "[%u] ", op->nframes); if (op->kt_ival1) seq_printf(m, "t1=%lld ", (long long)ktime_to_us(op->kt_ival1)); if (op->kt_ival2) seq_printf(m, "t2=%lld ", (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); return 0; } #endif /* CONFIG_PROC_FS */ /* * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface * of the given bcm tx op */ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; int err; /* no target device? => exit */ if (!op->ifindex) return; dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ return; } skb = alloc_skb(op->cfsiz + sizeof(struct can_skb_priv), gfp_any()); if (!skb) goto out; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; skb_put_data(skb, cf, op->cfsiz); /* send with loopback */ skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); if (!err) op->frames_abs++; op->currframe++; /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; out: dev_put(dev); } /* * bcm_send_to_user - send a BCM message to the userspace * (consisting of bcm_msg_head + x CAN frames) */ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, struct canfd_frame *frames, int has_timestamp) { struct sk_buff *skb; struct canfd_frame *firstframe; struct sockaddr_can *addr; struct sock *sk = op->sk; unsigned int datalen = head->nframes * op->cfsiz; int err; unsigned int *pflags; skb = alloc_skb(sizeof(*head) + datalen, gfp_any()); if (!skb) return; skb_put_data(skb, head, sizeof(*head)); /* ensure space for sockaddr_can and msg flags */ sock_skb_cb_check_size(sizeof(struct sockaddr_can) + sizeof(unsigned int)); /* initialize msg flags */ pflags = bcm_flags(skb); *pflags = 0; if (head->nframes) { /* CAN frames starting here */ firstframe = (struct canfd_frame *)skb_tail_pointer(skb); skb_put_data(skb, frames, datalen); /* * the BCM uses the flags-element of the canfd_frame * structure for internal purposes. This is only * relevant for updates that are generated by the * BCM, where nframes is 1 */ if (head->nframes == 1) { if (firstframe->flags & RX_LOCAL) *pflags |= MSG_DONTROUTE; if (firstframe->flags & RX_OWN) *pflags |= MSG_CONFIRM; firstframe->flags &= BCM_CAN_FLAGS_MASK; } } if (has_timestamp) { /* restore rx timestamp */ skb->tstamp = op->rx_stamp; } /* * Put the datagram to the queue so that bcm_recvmsg() can * get it from there. We need to pass the interface index to * bcm_recvmsg(). We pass a whole struct sockaddr_can in skb->cb * containing the interface index. */ addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = op->rx_ifindex; err = sock_queue_rcv_skb(sk, skb); if (err < 0) { struct bcm_sock *bo = bcm_sk(sk); kfree_skb(skb); /* don't care about overflows in this statistic */ bo->dropped_usr_msgs++; } } static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { ktime_t ival; if (op->kt_ival1 && op->count) ival = op->kt_ival1; else if (op->kt_ival2) ival = op->kt_ival2; else return false; hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); return true; } static void bcm_tx_start_timer(struct bcm_op *op) { if (bcm_tx_set_expiry(op, &op->timer)) hrtimer_start_expires(&op->timer, HRTIMER_MODE_ABS_SOFT); } /* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { op->count--; if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; msg_head.ival1 = op->ival1; msg_head.ival2 = op->ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); } bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); } return bcm_tx_set_expiry(op, &op->timer) ? HRTIMER_RESTART : HRTIMER_NORESTART; } /* * bcm_rx_changed - create a RX_CHANGED notification due to changed content */ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) { struct bcm_msg_head head; /* update statistics */ op->frames_filtered++; /* prevent statistics overflow */ if (op->frames_filtered > ULONG_MAX/100) op->frames_filtered = op->frames_abs = 0; /* this element is not throttled anymore */ data->flags &= ~RX_THR; memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; head.ival1 = op->ival1; head.ival2 = op->ival2; head.can_id = op->can_id; head.nframes = 1; bcm_send_to_user(op, &head, data, 1); } /* * bcm_rx_update_and_send - process a detected relevant receive content change * 1. update the last received data * 2. send a notification to the user (if possible) */ static void bcm_rx_update_and_send(struct bcm_op *op, struct canfd_frame *lastdata, const struct canfd_frame *rxdata, unsigned char traffic_flags) { memcpy(lastdata, rxdata, op->cfsiz); /* mark as used and throttled by default */ lastdata->flags |= (RX_RECV|RX_THR); /* add own/local/remote traffic flags */ lastdata->flags |= traffic_flags; /* throttling mode inactive ? */ if (!op->kt_ival2) { /* send RX_CHANGED to the user immediately */ bcm_rx_changed(op, lastdata); return; } /* with active throttling timer we are just done here */ if (hrtimer_active(&op->thrtimer)) return; /* first reception with enabled throttling mode */ if (!op->kt_lastmsg) goto rx_changed_settime; /* got a second frame inside a potential throttle period? */ if (ktime_us_delta(ktime_get(), op->kt_lastmsg) < ktime_to_us(op->kt_ival2)) { /* do not send the saved data - only start throttle timer */ hrtimer_start(&op->thrtimer, ktime_add(op->kt_lastmsg, op->kt_ival2), HRTIMER_MODE_ABS_SOFT); return; } /* the gap was that big, that throttling was not needed here */ rx_changed_settime: bcm_rx_changed(op, lastdata); op->kt_lastmsg = ktime_get(); } /* * bcm_rx_cmp_to_index - (bit)compares the currently received data to formerly * received data stored in op->last_frames[] */ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, const struct canfd_frame *rxdata, unsigned char traffic_flags) { struct canfd_frame *cf = op->frames + op->cfsiz * index; struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; int i; /* * no one uses the MSBs of flags for comparison, * so we use it here to detect the first time of reception */ if (!(lcf->flags & RX_RECV)) { /* received data for the first time => send update to user */ bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } /* do a real check in CAN frame data section */ for (i = 0; i < rxdata->len; i += 8) { if ((get_u64(cf, i) & get_u64(rxdata, i)) != (get_u64(cf, i) & get_u64(lcf, i))) { bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } if (op->flags & RX_CHECK_DLC) { /* do a real check in CAN frame length */ if (rxdata->len != lcf->len) { bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } } /* * bcm_rx_starttimer - enable timeout monitoring for CAN frame reception */ static void bcm_rx_starttimer(struct bcm_op *op) { if (op->flags & RX_NO_AUTOTIMER) return; if (op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } /* bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out */ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; /* if user wants to be informed, when cyclic CAN-Messages come back */ if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { /* clear received CAN frames to indicate 'nothing received' */ memset(op->last_frames, 0, op->nframes * op->cfsiz); } /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; msg_head.ival1 = op->ival1; msg_head.ival2 = op->ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); return HRTIMER_NORESTART; } /* * bcm_rx_do_flush - helper for bcm_rx_thr_flush */ static inline int bcm_rx_do_flush(struct bcm_op *op, unsigned int index) { struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; if ((op->last_frames) && (lcf->flags & RX_THR)) { bcm_rx_changed(op, lcf); return 1; } return 0; } /* * bcm_rx_thr_flush - Check for throttled data and send it to the userspace */ static int bcm_rx_thr_flush(struct bcm_op *op) { int updated = 0; if (op->nframes > 1) { unsigned int i; /* for MUX filter we start at index 1 */ for (i = 1; i < op->nframes; i++) updated += bcm_rx_do_flush(op, i); } else { /* for RX_FILTER_ID and simple filter */ updated += bcm_rx_do_flush(op, 0); } return updated; } /* * bcm_rx_thr_handler - the time for blocked content updates is over now: * Check for throttled data and send it to the userspace */ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); if (bcm_rx_thr_flush(op)) { hrtimer_forward_now(hrtimer, op->kt_ival2); return HRTIMER_RESTART; } else { /* rearm throttle handling */ op->kt_lastmsg = 0; return HRTIMER_NORESTART; } } /* * bcm_rx_handler - handle a CAN frame reception */ static void bcm_rx_handler(struct sk_buff *skb, void *data) { struct bcm_op *op = (struct bcm_op *)data; const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data; unsigned int i; unsigned char traffic_flags; if (op->can_id != rxframe->can_id) return; /* make sure to handle the correct frame type (CAN / CAN FD) */ if (op->flags & CAN_FD_FRAME) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } /* disable timeout */ hrtimer_cancel(&op->timer); /* save rx timestamp */ op->rx_stamp = skb->tstamp; /* save originator for recvfrom() */ op->rx_ifindex = skb->dev->ifindex; /* update statistics */ op->frames_abs++; if (op->flags & RX_RTR_FRAME) { /* send reply for RTR-request (placed in op->frames[0]) */ bcm_can_tx(op); return; } /* compute flags to distinguish between own/local/remote CAN traffic */ traffic_flags = 0; if (skb->sk) { traffic_flags |= RX_LOCAL; if (skb->sk == op->sk) traffic_flags |= RX_OWN; } if (op->flags & RX_FILTER_ID) { /* the easiest case */ bcm_rx_update_and_send(op, op->last_frames, rxframe, traffic_flags); goto rx_starttimer; } if (op->nframes == 1) { /* simple compare with index 0 */ bcm_rx_cmp_to_index(op, 0, rxframe, traffic_flags); goto rx_starttimer; } if (op->nframes > 1) { /* * multiplex compare * * find the first multiplex mask that fits. * Remark: The MUX-mask is stored in index 0 - but only the * first 64 bits of the frame data[] are relevant (CAN FD) */ for (i = 1; i < op->nframes; i++) { if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) == (get_u64(op->frames, 0) & get_u64(op->frames + op->cfsiz * i, 0))) { bcm_rx_cmp_to_index(op, i, rxframe, traffic_flags); break; } } } rx_starttimer: bcm_rx_starttimer(op); } /* * helpers for bcm_op handling: find & delete bcm [rx|tx] op elements */ static struct bcm_op *bcm_find_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op; list_for_each_entry(op, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) return op; } return NULL; } static void bcm_free_op_rcu(struct rcu_head *rcu_head) { struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); if ((op->last_frames) && (op->last_frames != &op->last_sframe)) kfree(op->last_frames); kfree(op); } static void bcm_remove_op(struct bcm_op *op) { hrtimer_cancel(&op->timer); hrtimer_cancel(&op->thrtimer); call_rcu(&op->rcu, bcm_free_op_rcu); } static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) { if (op->rx_reg_dev == dev) { can_rx_unregister(dev_net(dev), dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); /* mark as removed subscription */ op->rx_reg_dev = NULL; } else printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device " "mismatch %p %p\n", op->rx_reg_dev, dev); } /* * bcm_delete_rx_op - find and remove a rx op (returns number of removed ops) */ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op, *n; list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { /* disable automatic timer on frame reception */ op->flags |= RX_NO_AUTOTIMER; /* * Don't care if we're bound or not (due to netdev * problems) can_rx_unregister() is always a save * thing to do here. */ if (op->ifindex) { /* * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() */ if (op->rx_reg_dev) { struct net_device *dev; dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (dev) { bcm_rx_unreg(dev, op); dev_put(dev); } } } else can_rx_unregister(sock_net(op->sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); list_del(&op->list); bcm_remove_op(op); return 1; /* done */ } } return 0; /* not found */ } /* * bcm_delete_tx_op - find and remove a tx op (returns number of removed ops) */ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op, *n; list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { list_del(&op->list); bcm_remove_op(op); return 1; /* done */ } } return 0; /* not found */ } /* * bcm_read_op - read out a bcm_op and send it to the user (for bcm_sendmsg) */ static int bcm_read_op(struct list_head *ops, struct bcm_msg_head *msg_head, int ifindex) { struct bcm_op *op = bcm_find_op(ops, msg_head, ifindex); if (!op) return -EINVAL; /* put current values into msg_head */ msg_head->flags = op->flags; msg_head->count = op->count; msg_head->ival1 = op->ival1; msg_head->ival2 = op->ival2; msg_head->nframes = op->nframes; bcm_send_to_user(op, msg_head, op->frames, 0); return MHSIZ; } /* * bcm_tx_setup - create or update a bcm tx op (for bcm_sendmsg) */ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, int ifindex, struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; struct canfd_frame *cf; unsigned int i; int err; /* we need a real device to send frames */ if (!ifindex) return -ENODEV; /* check nframes boundaries - we need at least one CAN frame */ if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES) return -EINVAL; /* check timeval limitations */ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) return -EINVAL; /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { /* update existing BCM operation */ /* * Do we need more space for the CAN frames than currently * allocated? -> This is a _really_ unusual use-case and * therefore (complexity / locking) it is not supported. */ if (msg_head->nframes > op->nframes) return -E2BIG; /* update CAN frames content */ for (i = 0; i < msg_head->nframes; i++) { cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) err = -EINVAL; } else { if (cf->len > 8) err = -EINVAL; } if (err < 0) return err; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } op->flags = msg_head->flags; } else { /* insert new BCM operation for the given can_id */ op = kzalloc(OPSIZ, GFP_KERNEL); if (!op) return -ENOMEM; op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { op->frames = kmalloc_array(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->frames) { kfree(op); return -ENOMEM; } } else op->frames = &op->sframe; for (i = 0; i < msg_head->nframes; i++) { cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); if (err < 0) goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) err = -EINVAL; } else { if (cf->len > 8) err = -EINVAL; } if (err < 0) goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } /* tx_ops never compare with previous received messages */ op->last_frames = NULL; /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_tx_timeout_handler; /* currently unused in tx_ops */ hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); /* add this bcm_op to the list of the tx_ops */ list_add(&op->list, &bo->tx_ops); } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ if (op->nframes != msg_head->nframes) { op->nframes = msg_head->nframes; /* start multiple frame transmission with index 0 */ op->currframe = 0; } /* check flags */ if (op->flags & TX_RESET_MULTI_IDX) { /* start multiple frame transmission with index 0 */ op->currframe = 0; } if (op->flags & SETTIMER) { /* set timer values */ op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero values? */ if (!op->kt_ival1 && !op->kt_ival2) hrtimer_cancel(&op->timer); } if (op->flags & STARTTIMER) { hrtimer_cancel(&op->timer); /* spec: send CAN frame when starting timer */ op->flags |= TX_ANNOUNCE; } if (op->flags & TX_ANNOUNCE) { bcm_can_tx(op); if (op->count) op->count--; } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; free_op: if (op->frames != &op->sframe) kfree(op->frames); kfree(op); return err; } /* * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg) */ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, int ifindex, struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; int do_rx_register; int err = 0; if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) { /* be robust against wrong usage ... */ msg_head->flags |= RX_FILTER_ID; /* ignore trailing garbage */ msg_head->nframes = 0; } /* the first element contains the mux-mask => MAX_NFRAMES + 1 */ if (msg_head->nframes > MAX_NFRAMES + 1) return -EINVAL; if ((msg_head->flags & RX_RTR_FRAME) && ((msg_head->nframes != 1) || (!(msg_head->can_id & CAN_RTR_FLAG)))) return -EINVAL; /* check timeval limitations */ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) return -EINVAL; /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { /* update existing BCM operation */ /* * Do we need more space for the CAN frames than currently * allocated? -> This is a _really_ unusual use-case and * therefore (complexity / locking) it is not supported. */ if (msg_head->nframes > op->nframes) return -E2BIG; if (msg_head->nframes) { /* update CAN frames content */ err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) return err; /* clear last_frames to indicate 'nothing received' */ memset(op->last_frames, 0, msg_head->nframes * op->cfsiz); } op->nframes = msg_head->nframes; op->flags = msg_head->flags; /* Only an update -> do not call can_rx_register() */ do_rx_register = 0; } else { /* insert new BCM operation for the given can_id */ op = kzalloc(OPSIZ, GFP_KERNEL); if (!op) return -ENOMEM; op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; if (msg_head->nframes > 1) { /* create array for CAN frames and copy the data */ op->frames = kmalloc_array(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->frames) { kfree(op); return -ENOMEM; } /* create and init array for received CAN frames */ op->last_frames = kcalloc(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->last_frames) { kfree(op->frames); kfree(op); return -ENOMEM; } } else { op->frames = &op->sframe; op->last_frames = &op->last_sframe; } if (msg_head->nframes) { err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) { if (op->frames != &op->sframe) kfree(op->frames); if (op->last_frames != &op->last_sframe) kfree(op->last_frames); kfree(op); return err; } } /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; op->ifindex = ifindex; /* ifindex for timeout events w/o previous frame reception */ op->rx_ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_rx_timeout_handler; hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); op->thrtimer.function = bcm_rx_thr_handler; /* add this bcm_op to the list of the rx_ops */ list_add(&op->list, &bo->rx_ops); /* call can_rx_register() */ do_rx_register = 1; } /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */ /* check flags */ if (op->flags & RX_RTR_FRAME) { struct canfd_frame *frame0 = op->frames; /* no timers in RTR-mode */ hrtimer_cancel(&op->thrtimer); hrtimer_cancel(&op->timer); /* * funny feature in RX(!)_SETUP only for RTR-mode: * copy can_id into frame BUT without RTR-flag to * prevent a full-load-loopback-test ... ;-] */ if ((op->flags & TX_CP_CAN_ID) || (frame0->can_id == op->can_id)) frame0->can_id = op->can_id & ~CAN_RTR_FLAG; } else { if (op->flags & SETTIMER) { /* set timer value */ op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero value? */ if (!op->kt_ival1) hrtimer_cancel(&op->timer); /* * In any case cancel the throttle timer, flush * potentially blocked msgs and reset throttle handling */ op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); bcm_rx_thr_flush(op); } if ((op->flags & STARTTIMER) && op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } /* now we can register for can_ids, if we added a new bcm_op */ if (do_rx_register) { if (ifindex) { struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); if (dev) { err = can_rx_register(sock_net(sk), dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); op->rx_reg_dev = dev; dev_put(dev); } } else err = can_rx_register(sock_net(sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ list_del(&op->list); bcm_remove_op(op); return err; } } return msg_head->nframes * op->cfsiz + MHSIZ; } /* * bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg) */ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk, int cfsiz) { struct sk_buff *skb; struct net_device *dev; int err; /* we need a real device to send frames */ if (!ifindex) return -ENODEV; skb = alloc_skb(cfsiz + sizeof(struct can_skb_priv), GFP_KERNEL); if (!skb) return -ENOMEM; can_skb_reserve(skb); err = memcpy_from_msg(skb_put(skb, cfsiz), msg, cfsiz); if (err < 0) { kfree_skb(skb); return err; } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) { kfree_skb(skb); return -ENODEV; } can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; skb->dev = dev; can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ dev_put(dev); if (err) return err; return cfsiz + MHSIZ; } /* * bcm_sendmsg - process BCM commands (opcodes) from the userspace */ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); int ifindex = bo->ifindex; /* default ifindex for this bcm_op */ struct bcm_msg_head msg_head; int cfsiz; int ret; /* read bytes or error codes as return value */ if (!bo->bound) return -ENOTCONN; /* check for valid message length from userspace */ if (size < MHSIZ) return -EINVAL; /* read message head information */ ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ); if (ret < 0) return ret; cfsiz = CFSIZ(msg_head.flags); if ((size - MHSIZ) % cfsiz) return -EINVAL; /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < BCM_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; /* ifindex from sendto() */ ifindex = addr->can_ifindex; if (ifindex) { struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENODEV; if (dev->type != ARPHRD_CAN) { dev_put(dev); return -ENODEV; } dev_put(dev); } } lock_sock(sk); switch (msg_head.opcode) { case TX_SETUP: ret = bcm_tx_setup(&msg_head, msg, ifindex, sk); break; case RX_SETUP: ret = bcm_rx_setup(&msg_head, msg, ifindex, sk); break; case TX_DELETE: if (bcm_delete_tx_op(&bo->tx_ops, &msg_head, ifindex)) ret = MHSIZ; else ret = -EINVAL; break; case RX_DELETE: if (bcm_delete_rx_op(&bo->rx_ops, &msg_head, ifindex)) ret = MHSIZ; else ret = -EINVAL; break; case TX_READ: /* reuse msg_head for the reply to TX_READ */ msg_head.opcode = TX_STATUS; ret = bcm_read_op(&bo->tx_ops, &msg_head, ifindex); break; case RX_READ: /* reuse msg_head for the reply to RX_READ */ msg_head.opcode = RX_STATUS; ret = bcm_read_op(&bo->rx_ops, &msg_head, ifindex); break; case TX_SEND: /* we need exactly one CAN frame behind the msg head */ if ((msg_head.nframes != 1) || (size != cfsiz + MHSIZ)) ret = -EINVAL; else ret = bcm_tx_send(msg, ifindex, sk, cfsiz); break; default: ret = -EINVAL; break; } release_sock(sk); return ret; } /* * notification handler for netdevice status changes */ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, struct net_device *dev) { struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove device specific receive entries */ list_for_each_entry(op, &bo->rx_ops, list) if (op->rx_reg_dev == dev) bcm_rx_unreg(dev, op); /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { #if IS_ENABLED(CONFIG_PROC_FS) if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) { remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir); bo->bcm_proc_read = NULL; } #endif bo->bound = 0; bo->ifindex = 0; notify_enodev = 1; } release_sock(sk); if (notify_enodev) { sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } break; case NETDEV_DOWN: if (bo->bound && bo->ifindex == dev->ifindex) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } } } static int bcm_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&bcm_notifier_lock); list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { spin_unlock(&bcm_notifier_lock); bcm_notify(bcm_busy_notifier, msg, dev); spin_lock(&bcm_notifier_lock); } bcm_busy_notifier = NULL; spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } /* * initial settings for all BCM sockets to be set at socket creation time */ static int bcm_init(struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); bo->bound = 0; bo->ifindex = 0; bo->dropped_usr_msgs = 0; bo->bcm_proc_read = NULL; INIT_LIST_HEAD(&bo->tx_ops); INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ spin_lock(&bcm_notifier_lock); list_add_tail(&bo->notifier, &bcm_notifier_list); spin_unlock(&bcm_notifier_lock); return 0; } /* * standard socket functions */ static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; struct net *net; struct bcm_sock *bo; struct bcm_op *op, *next; if (!sk) return 0; net = sock_net(sk); bo = bcm_sk(sk); /* remove bcm_ops, timer, rx_unregister(), etc. */ spin_lock(&bcm_notifier_lock); while (bcm_busy_notifier == bo) { spin_unlock(&bcm_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&bcm_notifier_lock); } list_del(&bo->notifier); spin_unlock(&bcm_notifier_lock); lock_sock(sk); #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) remove_proc_entry(bo->procname, net->can.bcmproc_dir); #endif /* CONFIG_PROC_FS */ list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); list_for_each_entry_safe(op, next, &bo->rx_ops, list) { /* * Don't care if we're bound or not (due to netdev problems) * can_rx_unregister() is always a save thing to do here. */ if (op->ifindex) { /* * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() */ if (op->rx_reg_dev) { struct net_device *dev; dev = dev_get_by_index(net, op->ifindex); if (dev) { bcm_rx_unreg(dev, op); dev_put(dev); } } } else can_rx_unregister(net, NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); } synchronize_rcu(); list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); /* remove device reference */ if (bo->bound) { bo->bound = 0; bo->ifindex = 0; } sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, int flags) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); struct net *net = sock_net(sk); int ret = 0; if (len < BCM_MIN_NAMELEN) return -EINVAL; lock_sock(sk); if (bo->bound) { ret = -EISCONN; goto fail; } /* bind a device to this socket */ if (addr->can_ifindex) { struct net_device *dev; dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { ret = -ENODEV; goto fail; } if (dev->type != ARPHRD_CAN) { dev_put(dev); ret = -ENODEV; goto fail; } bo->ifindex = dev->ifindex; dev_put(dev); } else { /* no interface reference for ifindex = 0 ('any' CAN device) */ bo->ifindex = 0; } #if IS_ENABLED(CONFIG_PROC_FS) if (net->can.bcmproc_dir) { /* unique socket address as filename */ sprintf(bo->procname, "%lu", sock_i_ino(sk)); bo->bcm_proc_read = proc_create_net_single(bo->procname, 0644, net->can.bcmproc_dir, bcm_proc_show, sk); if (!bo->bcm_proc_read) { ret = -ENOMEM; goto fail; } } #endif /* CONFIG_PROC_FS */ bo->bound = 1; fail: release_sock(sk); return ret; } static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int error = 0; int err; skb = skb_recv_datagram(sk, flags, &error); if (!skb) return error; if (skb->len < size) size = skb->len; err = memcpy_to_msg(msg, skb->data, size); if (err < 0) { skb_free_datagram(sk, skb); return err; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(BCM_MIN_NAMELEN); msg->msg_namelen = BCM_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* assign the flags that have been recorded in bcm_send_to_user() */ msg->msg_flags |= *(bcm_flags(skb)); skb_free_datagram(sk, skb); return size; } static int bcm_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops bcm_ops = { .family = PF_CAN, .release = bcm_release, .bind = sock_no_bind, .connect = bcm_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = bcm_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = bcm_sendmsg, .recvmsg = bcm_recvmsg, .mmap = sock_no_mmap, }; static struct proto bcm_proto __read_mostly = { .name = "CAN_BCM", .owner = THIS_MODULE, .obj_size = sizeof(struct bcm_sock), .init = bcm_init, }; static const struct can_proto bcm_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_BCM, .ops = &bcm_ops, .prot = &bcm_proto, }; static int canbcm_pernet_init(struct net *net) { #if IS_ENABLED(CONFIG_PROC_FS) /* create /proc/net/can-bcm directory */ net->can.bcmproc_dir = proc_net_mkdir(net, "can-bcm", net->proc_net); #endif /* CONFIG_PROC_FS */ return 0; } static void canbcm_pernet_exit(struct net *net) { #if IS_ENABLED(CONFIG_PROC_FS) /* remove /proc/net/can-bcm directory */ if (net->can.bcmproc_dir) remove_proc_entry("can-bcm", net->proc_net); #endif /* CONFIG_PROC_FS */ } static struct pernet_operations canbcm_pernet_ops __read_mostly = { .init = canbcm_pernet_init, .exit = canbcm_pernet_exit, }; static struct notifier_block canbcm_notifier = { .notifier_call = bcm_notifier }; static int __init bcm_module_init(void) { int err; pr_info("can: broadcast manager protocol\n"); err = register_pernet_subsys(&canbcm_pernet_ops); if (err) return err; err = register_netdevice_notifier(&canbcm_notifier); if (err) goto register_notifier_failed; err = can_proto_register(&bcm_can_proto); if (err < 0) { printk(KERN_ERR "can: registration of bcm protocol failed\n"); goto register_proto_failed; } return 0; register_proto_failed: unregister_netdevice_notifier(&canbcm_notifier); register_notifier_failed: unregister_pernet_subsys(&canbcm_pernet_ops); return err; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } module_init(bcm_module_init); module_exit(bcm_module_exit); |
| 136 613 243 1 243 243 241 213 215 605 605 54 54 581 582 582 273 273 205 207 206 214 544 516 517 515 292 292 292 266 267 95 95 106 106 55 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * iw_table is the sysfs-set interleave weight table, a value of 0 denotes * system-default value should be used. A NULL iw_table also denotes that * system-default values should be used. Until the system-default table * is implemented, the system-default is always 1. * * iw_table is RCU protected */ static u8 __rcu *iw_table; static DEFINE_MUTEX(iw_table_lock); static u8 get_il_weight(int node) { u8 *table; u8 weight; rcu_read_lock(); table = rcu_dereference(iw_table); /* if no iw_table, use system default */ weight = table ? table[node] : 1; /* if value in iw_table is 0, use system default */ weight = weight ? weight : 1; rcu_read_unlock(); return weight; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed++; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_likely_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table; unsigned int weight_total = 0; u8 weight; int nid; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); table = rcu_dereference(iw_table); /* calculate the total weight */ for_each_node_mask(nid, nodemask) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; weight_total += weight; } /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; weight = weight ? weight : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_frozen_pages_noprof( gfp | __GFP_THISNODE | __GFP_NORETRY, order, nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, ilx, nid); if (!page) return NULL; set_page_refcounted(page); return page_rmappable_folio(page); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_frozen_pages_noprof(gfp, order); if (page) set_page_refcounted(page); return page; } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *table, *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); table = rcu_dereference(iw_table); if (table) memcpy(weights, table, nr_node_ids); rcu_read_unlock(); /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) { if (!weights[node]) weights[node] = 1; weight_total += weights[node]; } /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct iw_node_attr *node_attr; u8 *new; u8 *old; u8 weight = 0; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "")) weight = 0; else if (kstrtou8(buf, 0, &weight)) return -EINVAL; new = kzalloc(nr_node_ids, GFP_KERNEL); if (!new) return -ENOMEM; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); if (old) memcpy(new, old, nr_node_ids); new[node_attr->nid] = weight; rcu_assign_pointer(iw_table, new); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); return count; } static struct iw_node_attr **node_attrs; static void sysfs_wi_node_release(struct iw_node_attr *node_attr, struct kobject *parent) { if (!node_attr) return; sysfs_remove_file(parent, &node_attr->kobj_attr.attr); kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); } static void sysfs_wi_release(struct kobject *wi_kobj) { int i; for (i = 0; i < nr_node_ids; i++) sysfs_wi_node_release(node_attrs[i], wi_kobj); kobject_put(wi_kobj); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = sysfs_wi_release, }; static int add_weight_node(int nid, struct kobject *wi_kobj) { struct iw_node_attr *node_attr; char *name; node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL); if (!node_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(node_attr); return -ENOMEM; } sysfs_attr_init(&node_attr->kobj_attr.attr); node_attr->kobj_attr.attr.name = name; node_attr->kobj_attr.attr.mode = 0644; node_attr->kobj_attr.show = node_show; node_attr->kobj_attr.store = node_store; node_attr->nid = nid; if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) { kfree(node_attr->kobj_attr.attr.name); kfree(node_attr); pr_err("failed to add attribute to weighted_interleave\n"); return -ENOMEM; } node_attrs[nid] = node_attr; return 0; } static int add_weighted_interleave_group(struct kobject *root_kobj) { struct kobject *wi_kobj; int nid, err; wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL); if (!wi_kobj) return -ENOMEM; err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj, "weighted_interleave"); if (err) { kfree(wi_kobj); return err; } for_each_node_state(nid, N_POSSIBLE) { err = add_weight_node(nid, wi_kobj); if (err) { pr_err("failed to add sysfs [node%d]\n", nid); break; } } if (err) kobject_put(wi_kobj); return 0; } static void mempolicy_kobj_release(struct kobject *kobj) { u8 *old; mutex_lock(&iw_table_lock); old = rcu_dereference_protected(iw_table, lockdep_is_held(&iw_table_lock)); rcu_assign_pointer(iw_table, NULL); mutex_unlock(&iw_table_lock); synchronize_rcu(); kfree(old); kfree(node_attrs); kfree(kobj); } static const struct kobj_type mempolicy_ktype = { .release = mempolicy_kobj_release }; static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL); if (!mempolicy_kobj) { err = -ENOMEM; goto err_out; } node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *), GFP_KERNEL); if (!node_attrs) { err = -ENOMEM; goto mempol_out; } err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj, "mempolicy"); if (err) goto node_out; err = add_weighted_interleave_group(mempolicy_kobj); if (err) { pr_err("mempolicy sysfs structure failed to initialize\n"); kobject_put(mempolicy_kobj); return err; } return err; node_out: kfree(node_attrs); mempol_out: kfree(mempolicy_kobj); err_out: pr_err("failed to add mempolicy kobject to the system\n"); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 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 | // SPDX-License-Identifier: GPL-2.0 /* Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #include <linux/nexthop.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/lwtunnel.h> #include <net/ndisc.h> #include <net/nexthop.h> #include <net/route.h> #include <net/sock.h> #define NH_RES_DEFAULT_IDLE_TIMER (120 * HZ) #define NH_RES_DEFAULT_UNBALANCED_TIMER 0 /* No forced rebalancing. */ static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo); #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) #define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ NHA_OP_FLAG_DUMP_HW_STATS) static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, [NHA_GROUP_TYPE] = { .type = NLA_U16 }, [NHA_BLACKHOLE] = { .type = NLA_FLAG }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_GATEWAY] = { .type = NLA_BINARY }, [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_policy_del[] = { [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_OIF] = { .type = NLA_U32 }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { [NHA_RES_GROUP_BUCKETS] = { .type = NLA_U16 }, [NHA_RES_GROUP_IDLE_TIMER] = { .type = NLA_U32 }, [NHA_RES_GROUP_UNBALANCED_TIMER] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump_bucket[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_RES_BUCKET] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_res_bucket_policy_dump[] = { [NHA_RES_BUCKET_NH_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_get_bucket[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_RES_BUCKET] = { .type = NLA_NESTED }, }; static const struct nla_policy rtm_nh_res_bucket_policy_get[] = { [NHA_RES_BUCKET_INDEX] = { .type = NLA_U16 }, }; static bool nexthop_notifiers_is_empty(struct net *net) { return !net->nexthop.notifier_chain.head; } static void __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, const struct nh_info *nhi) { nh_info->dev = nhi->fib_nhc.nhc_dev; nh_info->gw_family = nhi->fib_nhc.nhc_gw_family; if (nh_info->gw_family == AF_INET) nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4; else if (nh_info->gw_family == AF_INET6) nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; nh_info->id = nhi->nh_parent->id; nh_info->is_reject = nhi->reject_nh; nh_info->is_fdb = nhi->fdb_nh; nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; } static int nh_notifier_single_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); info->type = NH_NOTIFIER_INFO_TYPE_SINGLE; info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); if (!info->nh) return -ENOMEM; __nh_notifier_single_info_init(info->nh, nhi); return 0; } static void nh_notifier_single_info_fini(struct nh_notifier_info *info) { kfree(info->nh); } static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, struct nh_group *nhg) { u16 num_nh = nhg->num_nh; int i; info->type = NH_NOTIFIER_INFO_TYPE_GRP; info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh), GFP_KERNEL); if (!info->nh_grp) return -ENOMEM; info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; nhi = rtnl_dereference(nhge->nh->nh_info); info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, nhi); } return 0; } static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, struct nh_group *nhg) { struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); u16 num_nh_buckets = res_table->num_nh_buckets; unsigned long size; u16 i; info->type = NH_NOTIFIER_INFO_TYPE_RES_TABLE; size = struct_size(info->nh_res_table, nhs, num_nh_buckets); info->nh_res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (!info->nh_res_table) return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; struct nh_info *nhi; nhge = rtnl_dereference(bucket->nh_entry); nhi = rtnl_dereference(nhge->nh->nh_info); __nh_notifier_single_info_init(&info->nh_res_table->nhs[i], nhi); } return 0; } static int nh_notifier_grp_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->hash_threshold) return nh_notifier_mpath_info_init(info, nhg); else if (nhg->resilient) return nh_notifier_res_table_info_init(info, nhg); return -EINVAL; } static void nh_notifier_grp_info_fini(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->hash_threshold) kfree(info->nh_grp); else if (nhg->resilient) vfree(info->nh_res_table); } static int nh_notifier_info_init(struct nh_notifier_info *info, const struct nexthop *nh) { info->id = nh->id; if (nh->is_group) return nh_notifier_grp_info_init(info, nh); else return nh_notifier_single_info_init(info, nh); } static void nh_notifier_info_fini(struct nh_notifier_info *info, const struct nexthop *nh) { if (nh->is_group) nh_notifier_grp_info_fini(info, nh); else nh_notifier_single_info_fini(info); } static int call_nexthop_notifiers(struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, }; int err; ASSERT_RTNL(); if (nexthop_notifiers_is_empty(net)) return 0; err = nh_notifier_info_init(&info, nh); if (err) { NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); return err; } err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, event_type, &info); nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } static int nh_notifier_res_bucket_idle_timer_get(const struct nh_notifier_info *info, bool force, unsigned int *p_idle_timer_ms) { struct nh_res_table *res_table; struct nh_group *nhg; struct nexthop *nh; int err = 0; /* When 'force' is false, nexthop bucket replacement is performed * because the bucket was deemed to be idle. In this case, capable * listeners can choose to perform an atomic replacement: The bucket is * only replaced if it is inactive. However, if the idle timer interval * is smaller than the interval in which a listener is querying * buckets' activity from the device, then atomic replacement should * not be tried. Pass the idle timer value to listeners, so that they * could determine which type of replacement to perform. */ if (force) { *p_idle_timer_ms = 0; return 0; } rcu_read_lock(); nh = nexthop_find_by_id(info->net, info->id); if (!nh) { err = -EINVAL; goto out; } nhg = rcu_dereference(nh->nh_grp); res_table = rcu_dereference(nhg->res_table); *p_idle_timer_ms = jiffies_to_msecs(res_table->idle_timer); out: rcu_read_unlock(); return err; } static int nh_notifier_res_bucket_info_init(struct nh_notifier_info *info, u16 bucket_index, bool force, struct nh_info *oldi, struct nh_info *newi) { unsigned int idle_timer_ms; int err; err = nh_notifier_res_bucket_idle_timer_get(info, force, &idle_timer_ms); if (err) return err; info->type = NH_NOTIFIER_INFO_TYPE_RES_BUCKET; info->nh_res_bucket = kzalloc(sizeof(*info->nh_res_bucket), GFP_KERNEL); if (!info->nh_res_bucket) return -ENOMEM; info->nh_res_bucket->bucket_index = bucket_index; info->nh_res_bucket->idle_timer_ms = idle_timer_ms; info->nh_res_bucket->force = force; __nh_notifier_single_info_init(&info->nh_res_bucket->old_nh, oldi); __nh_notifier_single_info_init(&info->nh_res_bucket->new_nh, newi); return 0; } static void nh_notifier_res_bucket_info_fini(struct nh_notifier_info *info) { kfree(info->nh_res_bucket); } static int __call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, u16 bucket_index, bool force, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, .id = nhg_id, }; int err; if (nexthop_notifiers_is_empty(net)) return 0; err = nh_notifier_res_bucket_info_init(&info, bucket_index, force, oldi, newi); if (err) return err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_BUCKET_REPLACE, &info); nh_notifier_res_bucket_info_fini(&info); return notifier_to_errno(err); } /* There are three users of RES_TABLE, and NHs etc. referenced from there: * * 1) a collection of callbacks for NH maintenance. This operates under * RTNL, * 2) the delayed work that gradually balances the resilient table, * 3) and nexthop_select_path(), operating under RCU. * * Both the delayed work and the RTNL block are writers, and need to * maintain mutual exclusion. Since there are only two and well-known * writers for each table, the RTNL code can make sure it has exclusive * access thus: * * - Have the DW operate without locking; * - synchronously cancel the DW; * - do the writing; * - if the write was not actually a delete, call upkeep, which schedules * DW again if necessary. * * The functions that are always called from the RTNL context use * rtnl_dereference(). The functions that can also be called from the DW do * a raw dereference and rely on the above mutual exclusion scheme. */ #define nh_res_dereference(p) (rcu_dereference_raw(p)) static int call_nexthop_res_bucket_notifiers(struct net *net, u32 nhg_id, u16 bucket_index, bool force, struct nexthop *old_nh, struct nexthop *new_nh, struct netlink_ext_ack *extack) { struct nh_info *oldi = nh_res_dereference(old_nh->nh_info); struct nh_info *newi = nh_res_dereference(new_nh->nh_info); return __call_nexthop_res_bucket_notifiers(net, nhg_id, bucket_index, force, oldi, newi, extack); } static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, .id = nh->id, }; struct nh_group *nhg; int err; ASSERT_RTNL(); if (nexthop_notifiers_is_empty(net)) return 0; /* At this point, the nexthop buckets are still not populated. Only * emit a notification with the logical nexthops, so that a listener * could potentially veto it in case of unsupported configuration. */ nhg = rtnl_dereference(nh->nh_grp); err = nh_notifier_mpath_info_init(&info, nhg); if (err) { NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); return err; } err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, &info); kfree(info.nh_grp); return notifier_to_errno(err); } static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, enum nexthop_event_type event_type, struct nexthop *nh, struct netlink_ext_ack *extack) { struct nh_notifier_info info = { .net = net, .extack = extack, }; int err; err = nh_notifier_info_init(&info, nh); if (err) return err; err = nb->notifier_call(nb, event_type, &info); nh_notifier_info_fini(&info, nh); return notifier_to_errno(err); } static unsigned int nh_dev_hashfn(unsigned int val) { unsigned int mask = NH_DEV_HASHSIZE - 1; return (val ^ (val >> NH_DEV_HASHBITS) ^ (val >> (NH_DEV_HASHBITS * 2))) & mask; } static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) { struct net_device *dev = nhi->fib_nhc.nhc_dev; struct hlist_head *head; unsigned int hash; WARN_ON(!dev); hash = nh_dev_hashfn(dev->ifindex); head = &net->nexthop.devhash[hash]; hlist_add_head(&nhi->dev_hash, head); } static void nexthop_free_group(struct nexthop *nh) { struct nh_group *nhg; int i; nhg = rcu_dereference_raw(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); free_percpu(nhge->stats); nexthop_put(nhge->nh); } WARN_ON(nhg->spare == nhg); if (nhg->resilient) vfree(rcu_dereference_raw(nhg->res_table)); kfree(nhg->spare); kfree(nhg); } static void nexthop_free_single(struct nexthop *nh) { struct nh_info *nhi; nhi = rcu_dereference_raw(nh->nh_info); switch (nhi->family) { case AF_INET: fib_nh_release(nh->net, &nhi->fib_nh); break; case AF_INET6: ipv6_stub->fib6_nh_release(&nhi->fib6_nh); break; } kfree(nhi); } void nexthop_free_rcu(struct rcu_head *head) { struct nexthop *nh = container_of(head, struct nexthop, rcu); if (nh->is_group) nexthop_free_group(nh); else nexthop_free_single(nh); kfree(nh); } EXPORT_SYMBOL_GPL(nexthop_free_rcu); static struct nexthop *nexthop_alloc(void) { struct nexthop *nh; nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL); if (nh) { INIT_LIST_HEAD(&nh->fi_list); INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); INIT_LIST_HEAD(&nh->fdb_list); } return nh; } static struct nh_group *nexthop_grp_alloc(u16 num_nh) { struct nh_group *nhg; nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; return nhg; } static void nh_res_table_upkeep_dw(struct work_struct *work); static struct nh_res_table * nexthop_res_table_alloc(struct net *net, u32 nhg_id, struct nh_config *cfg) { const u16 num_nh_buckets = cfg->nh_grp_res_num_buckets; struct nh_res_table *res_table; unsigned long size; size = struct_size(res_table, nh_buckets, num_nh_buckets); res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (!res_table) return NULL; res_table->net = net; res_table->nhg_id = nhg_id; INIT_DELAYED_WORK(&res_table->upkeep_dw, &nh_res_table_upkeep_dw); INIT_LIST_HEAD(&res_table->uw_nh_entries); res_table->idle_timer = cfg->nh_grp_res_idle_timer; res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; res_table->num_nh_buckets = num_nh_buckets; return res_table; } static void nh_base_seq_inc(struct net *net) { while (++net->nexthop.seq == 0) ; } /* no reference taken; rcu lock or rtnl must be held */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id) { struct rb_node **pp, *parent = NULL, *next; pp = &net->nexthop.rb_root.rb_node; while (1) { struct nexthop *nh; next = rcu_dereference_raw(*pp); if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (id < nh->id) pp = &next->rb_left; else if (id > nh->id) pp = &next->rb_right; else return nh; } return NULL; } EXPORT_SYMBOL_GPL(nexthop_find_by_id); /* used for auto id allocation; called with rtnl held */ static u32 nh_find_unused_id(struct net *net) { u32 id_start = net->nexthop.last_id_allocated; while (1) { net->nexthop.last_id_allocated++; if (net->nexthop.last_id_allocated == id_start) break; if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated)) return net->nexthop.last_id_allocated; } return 0; } static void nh_res_time_set_deadline(unsigned long next_time, unsigned long *deadline) { if (time_before(next_time, *deadline)) *deadline = next_time; } static clock_t nh_res_table_unbalanced_time(struct nh_res_table *res_table) { if (list_empty(&res_table->uw_nh_entries)) return 0; return jiffies_delta_to_clock_t(jiffies - res_table->unbalanced_since); } static int nla_put_nh_group_res(struct sk_buff *skb, struct nh_group *nhg) { struct nh_res_table *res_table = rtnl_dereference(nhg->res_table); struct nlattr *nest; nest = nla_nest_start(skb, NHA_RES_GROUP); if (!nest) return -EMSGSIZE; if (nla_put_u16(skb, NHA_RES_GROUP_BUCKETS, res_table->num_nh_buckets) || nla_put_u32(skb, NHA_RES_GROUP_IDLE_TIMER, jiffies_to_clock_t(res_table->idle_timer)) || nla_put_u32(skb, NHA_RES_GROUP_UNBALANCED_TIMER, jiffies_to_clock_t(res_table->unbalanced_timer)) || nla_put_u64_64bit(skb, NHA_RES_GROUP_UNBALANCED_TIME, nh_res_table_unbalanced_time(res_table), NHA_RES_GROUP_PAD)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) { struct nh_grp_entry_stats *cpu_stats; cpu_stats = get_cpu_ptr(nhge->stats); u64_stats_update_begin(&cpu_stats->syncp); u64_stats_inc(&cpu_stats->packets); u64_stats_update_end(&cpu_stats->syncp); put_cpu_ptr(cpu_stats); } static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, u64 *ret_packets) { int i; *ret_packets = 0; for_each_possible_cpu(i) { struct nh_grp_entry_stats *cpu_stats; unsigned int start; u64 packets; cpu_stats = per_cpu_ptr(nhge->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); packets = u64_stats_read(&cpu_stats->packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); *ret_packets += packets; } } static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, const struct nexthop *nh) { struct nh_group *nhg; int i; ASSERT_RTNL(); nhg = rtnl_dereference(nh->nh_grp); info->id = nh->id; info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, stats, nhg->num_nh), GFP_KERNEL); if (!info->nh_grp_hw_stats) return -ENOMEM; info->nh_grp_hw_stats->num_nh = nhg->num_nh; for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; } return 0; } static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) { kfree(info->nh_grp_hw_stats); } void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets) { info->hw_stats_used = true; info->stats[nh_idx].packets += delta_packets; } EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); static void nh_grp_hw_stats_apply_update(struct nexthop *nh, struct nh_notifier_info *info) { struct nh_group *nhg; int i; ASSERT_RTNL(); nhg = rtnl_dereference(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; } } static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) { struct nh_notifier_info info = { .net = nh->net, }; struct net *net = nh->net; int err; if (nexthop_notifiers_is_empty(net)) { *hw_stats_used = false; return 0; } err = nh_notifier_grp_hw_stats_init(&info, nh); if (err) return err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, &info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ nh_grp_hw_stats_apply_update(nh, &info); *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; nh_notifier_grp_hw_stats_fini(&info); return notifier_to_errno(err); } static int nla_put_nh_group_stats_entry(struct sk_buff *skb, struct nh_grp_entry *nhge, u32 op_flags) { struct nlattr *nest; u64 packets; nh_grp_entry_stats_read(nhge, &packets); nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, packets + nhge->packets_hw)) goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, nhge->packets_hw)) goto nla_put_failure; nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, u32 op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nlattr *nest; bool hw_stats_used; int err; int i; if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) goto err_out; if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && nhg->hw_stats) { err = nh_grp_hw_stats_update(nh, &hw_stats_used); if (err) goto out; if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) goto err_out; } nest = nla_nest_start(skb, NHA_GROUP_STATS); if (!nest) goto err_out; for (i = 0; i < nhg->num_nh; i++) if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], op_flags)) goto cancel_out; nla_nest_end(skb, nest); return 0; cancel_out: nla_nest_cancel(skb, nest); err_out: err = -EMSGSIZE; out: return err; } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, u32 op_flags, u32 *resp_op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; u16 weight; int i; *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; if (nhg->hash_threshold) group_type = NEXTHOP_GRP_TYPE_MPATH; else if (nhg->resilient) group_type = NEXTHOP_GRP_TYPE_RES; if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type)) goto nla_put_failure; nla = nla_reserve(skb, NHA_GROUP, len); if (!nla) goto nla_put_failure; p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { weight = nhg->nh_entries[i].weight - 1; *p++ = (struct nexthop_grp) { .id = nhg->nh_entries[i].nh->id, .weight = weight, .weight_high = weight >> 8, }; } if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; if (op_flags & NHA_OP_FLAG_DUMP_STATS && (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || nla_put_nh_group_stats(skb, nh, op_flags))) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, int event, u32 portid, u32 seq, unsigned int nlflags, u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; struct nlmsghdr *nlh; struct nh_info *nhi; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = nh->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); u32 resp_op_flags = 0; if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) || nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags)) goto nla_put_failure; goto out; } nhi = rtnl_dereference(nh->nh_info); nhm->nh_family = nhi->family; if (nhi->reject_nh) { if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; } else if (nhi->fdb_nh) { if (nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; } else { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex)) goto nla_put_failure; } nhm->nh_scope = nhi->fib_nhc.nhc_scope; switch (nhi->family) { case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; case AF_INET6: fib6_nh = &nhi->fib6_nh; if (fib6_nh->fib_nh_gw_family && nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6)) goto nla_put_failure; break; } if (nhi->fib_nhc.nhc_lwtstate && lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, NHA_ENCAP, NHA_ENCAP_TYPE) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static size_t nh_nlmsg_size_grp_res(struct nh_group *nhg) { return nla_total_size(0) + /* NHA_RES_GROUP */ nla_total_size(2) + /* NHA_RES_GROUP_BUCKETS */ nla_total_size(4) + /* NHA_RES_GROUP_IDLE_TIMER */ nla_total_size(4) + /* NHA_RES_GROUP_UNBALANCED_TIMER */ nla_total_size_64bit(8);/* NHA_RES_GROUP_UNBALANCED_TIME */ } static size_t nh_nlmsg_size_grp(struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh; size_t tot = nla_total_size(sz) + nla_total_size(2); /* NHA_GROUP_TYPE */ if (nhg->resilient) tot += nh_nlmsg_size_grp_res(nhg); return tot; } static size_t nh_nlmsg_size_single(struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); size_t sz; /* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE * are mutually exclusive */ sz = nla_total_size(4); /* NHA_OIF */ switch (nhi->family) { case AF_INET: if (nhi->fib_nh.fib_nh_gw_family) sz += nla_total_size(4); /* NHA_GATEWAY */ break; case AF_INET6: /* NHA_GATEWAY */ if (nhi->fib6_nh.fib_nh_gw_family) sz += nla_total_size(sizeof(const struct in6_addr)); break; } if (nhi->fib_nhc.nhc_lwtstate) { sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate); sz += nla_total_size(2); /* NHA_ENCAP_TYPE */ } return sz; } static size_t nh_nlmsg_size(struct nexthop *nh) { size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg)); sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) sz += nh_nlmsg_size_grp(nh) + nla_total_size(4) + /* NHA_OP_FLAGS */ 0; else sz += nh_nlmsg_size_single(nh); return sz; } static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) { unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any()); if (!skb) goto errout; err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) { return (unsigned long)atomic_long_read(&bucket->used_time); } static unsigned long nh_res_bucket_idle_point(const struct nh_res_table *res_table, const struct nh_res_bucket *bucket, unsigned long now) { unsigned long time = nh_res_bucket_used_time(bucket); /* Bucket was not used since it was migrated. The idle time is now. */ if (time == bucket->migrated_time) return now; return time + res_table->idle_timer; } static unsigned long nh_res_table_unb_point(const struct nh_res_table *res_table) { return res_table->unbalanced_since + res_table->unbalanced_timer; } static void nh_res_bucket_set_idle(const struct nh_res_table *res_table, struct nh_res_bucket *bucket) { unsigned long now = jiffies; atomic_long_set(&bucket->used_time, (long)now); bucket->migrated_time = now; } static void nh_res_bucket_set_busy(struct nh_res_bucket *bucket) { atomic_long_set(&bucket->used_time, (long)jiffies); } static clock_t nh_res_bucket_idle_time(const struct nh_res_bucket *bucket) { unsigned long used_time = nh_res_bucket_used_time(bucket); return jiffies_delta_to_clock_t(jiffies - used_time); } static int nh_fill_res_bucket(struct sk_buff *skb, struct nexthop *nh, struct nh_res_bucket *bucket, u16 bucket_index, int event, u32 portid, u32 seq, unsigned int nlflags, struct netlink_ext_ack *extack) { struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); struct nlmsghdr *nlh; struct nlattr *nest; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = bucket->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; nest = nla_nest_start(skb, NHA_RES_BUCKET); if (!nest) goto nla_put_failure; if (nla_put_u16(skb, NHA_RES_BUCKET_INDEX, bucket_index) || nla_put_u32(skb, NHA_RES_BUCKET_NH_ID, nhge->nh->id) || nla_put_u64_64bit(skb, NHA_RES_BUCKET_IDLE_TIME, nh_res_bucket_idle_time(bucket), NHA_RES_BUCKET_PAD)) goto nla_put_failure_nest; nla_nest_end(skb, nest); nlmsg_end(skb, nlh); return 0; nla_put_failure_nest: nla_nest_cancel(skb, nest); nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void nexthop_bucket_notify(struct nh_res_table *res_table, u16 bucket_index) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; struct nh_grp_entry *nhge = nh_res_dereference(bucket->nh_entry); struct nexthop *nh = nhge->nh_parent; struct sk_buff *skb; int err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto errout; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, 0, 0, NLM_F_REPLACE, NULL); if (err < 0) { kfree_skb(skb); goto errout; } rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, bool *is_fdb, struct netlink_ext_ack *extack) { if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); /* Nesting groups within groups is not supported. */ if (nhg->hash_threshold) { NL_SET_ERR_MSG(extack, "Hash-threshold group can not be a nexthop within a group"); return false; } if (nhg->resilient) { NL_SET_ERR_MSG(extack, "Resilient group can not be a nexthop within a group"); return false; } *is_fdb = nhg->fdb_nh; } else { struct nh_info *nhi = rtnl_dereference(nh->nh_info); if (nhi->reject_nh && npaths > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be used in a group with more than 1 path"); return false; } *is_fdb = nhi->fdb_nh; } return true; } static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, struct netlink_ext_ack *extack) { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (!nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); return -EINVAL; } if (*nh_family == AF_UNSPEC) { *nh_family = nhi->family; } else if (*nh_family != nhi->family) { NL_SET_ERR_MSG(extack, "FDB nexthop group cannot have mixed family nexthops"); return -EINVAL; } return 0; } static int nh_check_attr_group(struct net *net, struct nlattr *tb[], size_t tb_size, u16 nh_grp_type, struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int i, j; u8 nhg_fdb = 0; if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; } /* convert len to number of nexthop ids */ len /= sizeof(*nhg); nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { if (nhg[i].resvd2) { NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0"); return -EINVAL; } if (nexthop_grp_weight(&nhg[i]) == 0) { /* 0xffff got passed in, representing weight of 0x10000, * which is too heavy. */ NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } for (j = i + 1; j < len; ++j) { if (nhg[i].id == nhg[j].id) { NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group"); return -EINVAL; } } } if (tb[NHA_FDB]) nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { struct nexthop *nh; bool is_fdb_nh; nh = nexthop_find_by_id(net, nhg[i].id); if (!nh) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (!valid_group_nh(nh, len, &is_fdb_nh, extack)) return -EINVAL; if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) return -EINVAL; if (!nhg_fdb && is_fdb_nh) { NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); return -EINVAL; } } for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { if (!tb[i]) continue; switch (i) { case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) continue; break; } NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; } return 0; } static bool ipv6_good_nh(const struct fib6_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock(); n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); return !!(state & NUD_VALID); } static bool ipv4_good_nh(const struct fib_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); return !!(state & NUD_VALID); } static bool nexthop_is_good_nh(const struct nexthop *nh) { struct nh_info *nhi = rcu_dereference(nh->nh_info); switch (nhi->family) { case AF_INET: return ipv4_good_nh(&nhi->fib_nh); case AF_INET6: return ipv6_good_nh(&nhi->fib6_nh); } return false; } static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) { int i; for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; nh_grp_entry_stats_inc(nhge); return nhge->nh; } WARN_ON_ONCE(1); return NULL; } static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) return nexthop_select_path_fdb(nhg, hash); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ if (!nexthop_is_good_nh(nhge->nh)) continue; if (!nhge0) nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; nh_grp_entry_stats_inc(nhge); return nhge->nh; } if (!nhge0) nhge0 = &nhg->nh_entries[0]; nh_grp_entry_stats_inc(nhge0); return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) { struct nh_res_table *res_table = rcu_dereference(nhg->res_table); u16 bucket_index = hash % res_table->num_nh_buckets; struct nh_res_bucket *bucket; struct nh_grp_entry *nhge; /* nexthop_select_path() is expected to return a non-NULL value, so * skip protocol validation and just hand out whatever there is. */ bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); nh_grp_entry_stats_inc(nhge); return nhge->nh; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) { struct nh_group *nhg; if (!nh->is_group) return nh; nhg = rcu_dereference(nh->nh_grp); if (nhg->hash_threshold) return nexthop_select_path_hthr(nhg, hash); else if (nhg->resilient) return nexthop_select_path_res(nhg, hash); /* Unreachable. */ return NULL; } EXPORT_SYMBOL_GPL(nexthop_select_path); int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg) { struct nh_info *nhi; int err; if (nh->is_group) { struct nh_group *nhg; int i; nhg = rcu_dereference_rtnl(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhi = rcu_dereference_rtnl(nhge->nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } } else { nhi = rcu_dereference_rtnl(nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh); static int check_src_addr(const struct in6_addr *saddr, struct netlink_ext_ack *extack) { if (!ipv6_addr_any(saddr)) { NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects"); return -EINVAL; } return 0; } int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; bool is_fdb_nh; /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared * across multiple fib entries. If the config wants to use source * routing it can not use nexthop objects. mlxsw also does not allow * fib6_src on routes. */ if (cfg && check_src_addr(&cfg->fc_src, extack) < 0) return -EINVAL; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->has_v4) goto no_v4_nh; is_fdb_nh = nhg->fdb_nh; } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->family == AF_INET) goto no_v4_nh; is_fdb_nh = nhi->fdb_nh; } if (is_fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); return -EINVAL; } return 0; no_v4_nh: NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop"); return -EINVAL; } EXPORT_SYMBOL_GPL(fib6_check_nexthop); /* if existing nexthop has ipv6 routes linked to it, need * to verify this new spec works with ipv6 */ static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib6_info *f6i; if (list_empty(&old->f6i_list)) return 0; list_for_each_entry(f6i, &old->f6i_list, nh_list) { if (check_src_addr(&f6i->fib6_src.addr, extack) < 0) return -EINVAL; } return fib6_check_nexthop(new, NULL, extack); } static int nexthop_check_scope(struct nh_info *nhi, u8 scope, struct netlink_ext_ack *extack) { if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); return -EINVAL; } if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) { NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop"); return -EINVAL; } return 0; } /* Invoked by fib add code to verify nexthop by id is ok with * config for prefix; parts of fib_check_nh not done when nexthop * object is used. */ int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack) { struct nh_info *nhi; int err = 0; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } if (scope == RT_SCOPE_HOST) { NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); err = -EINVAL; goto out; } /* all nexthops in a group have the same scope */ nhi = rtnl_dereference(nhg->nh_entries[0].nh->nh_info); err = nexthop_check_scope(nhi, scope, extack); } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } err = nexthop_check_scope(nhi, scope, extack); } out: return err; } static int fib_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib_info *fi; list_for_each_entry(fi, &old->fi_list, nh_list) { int err; err = fib_check_nexthop(new, fi->fib_scope, extack); if (err) return err; } return 0; } static bool nh_res_nhge_is_balanced(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets == nhge->res.wants_buckets; } static bool nh_res_nhge_is_ow(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets > nhge->res.wants_buckets; } static bool nh_res_nhge_is_uw(const struct nh_grp_entry *nhge) { return nhge->res.count_buckets < nhge->res.wants_buckets; } static bool nh_res_table_is_balanced(const struct nh_res_table *res_table) { return list_empty(&res_table->uw_nh_entries); } static void nh_res_bucket_unset_nh(struct nh_res_bucket *bucket) { struct nh_grp_entry *nhge; if (bucket->occupied) { nhge = nh_res_dereference(bucket->nh_entry); nhge->res.count_buckets--; bucket->occupied = false; } } static void nh_res_bucket_set_nh(struct nh_res_bucket *bucket, struct nh_grp_entry *nhge) { nh_res_bucket_unset_nh(bucket); bucket->occupied = true; rcu_assign_pointer(bucket->nh_entry, nhge); nhge->res.count_buckets++; } static bool nh_res_bucket_should_migrate(struct nh_res_table *res_table, struct nh_res_bucket *bucket, unsigned long *deadline, bool *force) { unsigned long now = jiffies; struct nh_grp_entry *nhge; unsigned long idle_point; if (!bucket->occupied) { /* The bucket is not occupied, its NHGE pointer is either * NULL or obsolete. We _have to_ migrate: set force. */ *force = true; return true; } nhge = nh_res_dereference(bucket->nh_entry); /* If the bucket is populated by an underweight or balanced * nexthop, do not migrate. */ if (!nh_res_nhge_is_ow(nhge)) return false; /* At this point we know that the bucket is populated with an * overweight nexthop. It needs to be migrated to a new nexthop if * the idle timer of unbalanced timer expired. */ idle_point = nh_res_bucket_idle_point(res_table, bucket, now); if (time_after_eq(now, idle_point)) { /* The bucket is idle. We _can_ migrate: unset force. */ *force = false; return true; } /* Unbalanced timer of 0 means "never force". */ if (res_table->unbalanced_timer) { unsigned long unb_point; unb_point = nh_res_table_unb_point(res_table); if (time_after(now, unb_point)) { /* The bucket is not idle, but the unbalanced timer * expired. We _can_ migrate, but set force anyway, * so that drivers know to ignore activity reports * from the HW. */ *force = true; return true; } nh_res_time_set_deadline(unb_point, deadline); } nh_res_time_set_deadline(idle_point, deadline); return false; } static bool nh_res_bucket_migrate(struct nh_res_table *res_table, u16 bucket_index, bool notify, bool notify_nl, bool force) { struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index]; struct nh_grp_entry *new_nhge; struct netlink_ext_ack extack; int err; new_nhge = list_first_entry_or_null(&res_table->uw_nh_entries, struct nh_grp_entry, res.uw_nh_entry); if (WARN_ON_ONCE(!new_nhge)) /* If this function is called, "bucket" is either not * occupied, or it belongs to a next hop that is * overweight. In either case, there ought to be a * corresponding underweight next hop. */ return false; if (notify) { struct nh_grp_entry *old_nhge; old_nhge = nh_res_dereference(bucket->nh_entry); err = call_nexthop_res_bucket_notifiers(res_table->net, res_table->nhg_id, bucket_index, force, old_nhge->nh, new_nhge->nh, &extack); if (err) { pr_err_ratelimited("%s\n", extack._msg); if (!force) return false; /* It is not possible to veto a forced replacement, so * just clear the hardware flags from the nexthop * bucket to indicate to user space that this bucket is * not correctly populated in hardware. */ bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); } } nh_res_bucket_set_nh(bucket, new_nhge); nh_res_bucket_set_idle(res_table, bucket); if (notify_nl) nexthop_bucket_notify(res_table, bucket_index); if (nh_res_nhge_is_balanced(new_nhge)) list_del(&new_nhge->res.uw_nh_entry); return true; } #define NH_RES_UPKEEP_DW_MINIMUM_INTERVAL (HZ / 2) static void nh_res_table_upkeep(struct nh_res_table *res_table, bool notify, bool notify_nl) { unsigned long now = jiffies; unsigned long deadline; u16 i; /* Deadline is the next time that upkeep should be run. It is the * earliest time at which one of the buckets might be migrated. * Start at the most pessimistic estimate: either unbalanced_timer * from now, or if there is none, idle_timer from now. For each * encountered time point, call nh_res_time_set_deadline() to * refine the estimate. */ if (res_table->unbalanced_timer) deadline = now + res_table->unbalanced_timer; else deadline = now + res_table->idle_timer; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; bool force; if (nh_res_bucket_should_migrate(res_table, bucket, &deadline, &force)) { if (!nh_res_bucket_migrate(res_table, i, notify, notify_nl, force)) { unsigned long idle_point; /* A driver can override the migration * decision if the HW reports that the * bucket is actually not idle. Therefore * remark the bucket as busy again and * update the deadline. */ nh_res_bucket_set_busy(bucket); idle_point = nh_res_bucket_idle_point(res_table, bucket, now); nh_res_time_set_deadline(idle_point, &deadline); } } } /* If the group is still unbalanced, schedule the next upkeep to * either the deadline computed above, or the minimum deadline, * whichever comes later. */ if (!nh_res_table_is_balanced(res_table)) { unsigned long now = jiffies; unsigned long min_deadline; min_deadline = now + NH_RES_UPKEEP_DW_MINIMUM_INTERVAL; if (time_before(deadline, min_deadline)) deadline = min_deadline; queue_delayed_work(system_power_efficient_wq, &res_table->upkeep_dw, deadline - now); } } static void nh_res_table_upkeep_dw(struct work_struct *work) { struct delayed_work *dw = to_delayed_work(work); struct nh_res_table *res_table; res_table = container_of(dw, struct nh_res_table, upkeep_dw); nh_res_table_upkeep(res_table, true, true); } static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) { cancel_delayed_work_sync(&res_table->upkeep_dw); } static void nh_res_group_rebalance(struct nh_group *nhg, struct nh_res_table *res_table) { u16 prev_upper_bound = 0; u32 total = 0; u32 w = 0; int i; INIT_LIST_HEAD(&res_table->uw_nh_entries); for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; u16 upper_bound; u64 btw; w += nhge->weight; btw = ((u64)res_table->num_nh_buckets) * w; upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total); nhge->res.wants_buckets = upper_bound - prev_upper_bound; prev_upper_bound = upper_bound; if (nh_res_nhge_is_uw(nhge)) { if (list_empty(&res_table->uw_nh_entries)) res_table->unbalanced_since = jiffies; list_add(&nhge->res.uw_nh_entry, &res_table->uw_nh_entries); } } } /* Migrate buckets in res_table so that they reference NHGE's from NHG with * the right NH ID. Set those buckets that do not have a corresponding NHGE * entry in NHG as not occupied. */ static void nh_res_table_migrate_buckets(struct nh_res_table *res_table, struct nh_group *nhg) { u16 i; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; u32 id = rtnl_dereference(bucket->nh_entry)->nh->id; bool found = false; int j; for (j = 0; j < nhg->num_nh; j++) { struct nh_grp_entry *nhge = &nhg->nh_entries[j]; if (nhge->nh->id == id) { nh_res_bucket_set_nh(bucket, nhge); found = true; break; } } if (!found) nh_res_bucket_unset_nh(bucket); } } static void replace_nexthop_grp_res(struct nh_group *oldg, struct nh_group *newg) { /* For NH group replacement, the new NHG might only have a stub * hash table with 0 buckets, because the number of buckets was not * specified. For NH removal, oldg and newg both reference the same * res_table. So in any case, in the following, we want to work * with oldg->res_table. */ struct nh_res_table *old_res_table = rtnl_dereference(oldg->res_table); unsigned long prev_unbalanced_since = old_res_table->unbalanced_since; bool prev_has_uw = !list_empty(&old_res_table->uw_nh_entries); nh_res_table_cancel_upkeep(old_res_table); nh_res_table_migrate_buckets(old_res_table, newg); nh_res_group_rebalance(newg, old_res_table); if (prev_has_uw && !list_empty(&old_res_table->uw_nh_entries)) old_res_table->unbalanced_since = prev_unbalanced_since; nh_res_table_upkeep(old_res_table, true, false); } static void nh_hthr_group_rebalance(struct nh_group *nhg) { u32 total = 0; u32 w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; u32 upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; atomic_set(&nhge->hthr.upper_bound, upper_bound); } } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, struct nl_info *nlinfo) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; struct netlink_ext_ack extack; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; int i, j, err; WARN_ON(!nh); nhg = rtnl_dereference(nhp->nh_grp); newg = nhg->spare; /* last entry, keep it visible and remove the parent */ if (nhg->num_nh == 1) { remove_nexthop(net, nhp, nlinfo); return; } newg->has_v4 = false; newg->is_multipath = nhg->is_multipath; newg->hash_threshold = nhg->hash_threshold; newg->resilient = nhg->resilient; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; /* copy old entries to new except the one getting removed */ nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { struct nh_info *nhi; /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) newg->has_v4 = true; list_del(&nhges[i].nh_list); new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list); j++; } if (newg->hash_threshold) nh_hthr_group_rebalance(newg); else if (newg->resilient) replace_nexthop_grp_res(nhg, newg); rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through * bucket notifications. */ if (newg->hash_threshold) { err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack); if (err) pr_err("%s\n", extack._msg); } if (nlinfo) nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); struct nh_res_table *res_table; int i, num_nh = nhg->num_nh; for (i = 0; i < num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (WARN_ON(!nhge->nh)) continue; list_del_init(&nhge->nh_list); } if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); nh_res_table_cancel_upkeep(res_table); } } /* not called for nexthop replace */ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) { struct fib6_info *f6i, *tmp; bool do_flush = false; struct fib_info *fi; list_for_each_entry(fi, &nh->fi_list, nh_list) { fi->fib_flags |= RTNH_F_DEAD; do_flush = true; } if (do_flush) fib_flush(net); /* ip6_del_rt removes the entry from this list hence the _safe */ list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) { /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); ipv6_stub->ip6_del_rt(net, f6i, !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); } } static void __remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { __remove_nexthop_fib(net, nh); if (nh->is_group) { remove_nexthop_group(nh, nlinfo); } else { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (nhi->fib_nhc.nhc_dev) hlist_del(&nhi->dev_hash); remove_nexthop_from_groups(net, nh, nlinfo); } } static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL); /* remove from the tree */ rb_erase(&nh->rb_node, &net->nexthop.rb_root); if (nlinfo) nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo); __remove_nexthop(net, nh, nlinfo); nh_base_seq_inc(net); nexthop_put(nh); } /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, struct nexthop *replaced_nh) { struct fib6_info *f6i; struct nh_group *nhg; int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); /* if an IPv6 group was replaced, we have to release all old * dsts to make sure all refcounts are released */ if (!replaced_nh->is_group) return; nhg = rtnl_dereference(replaced_nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); if (nhi->family == AF_INET6) ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_res_table *tmp_table = NULL; struct nh_res_table *new_res_table; struct nh_res_table *old_res_table; struct nh_group *oldg, *newg; int i, err; if (!new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop."); return -EINVAL; } oldg = rtnl_dereference(old->nh_grp); newg = rtnl_dereference(new->nh_grp); if (newg->hash_threshold != oldg->hash_threshold) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with one of a different type."); return -EINVAL; } if (newg->hash_threshold) { err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; } else if (newg->resilient) { new_res_table = rtnl_dereference(newg->res_table); old_res_table = rtnl_dereference(oldg->res_table); /* Accept if num_nh_buckets was not given, but if it was * given, demand that the value be correct. */ if (cfg->nh_grp_res_has_num_buckets && cfg->nh_grp_res_num_buckets != old_res_table->num_nh_buckets) { NL_SET_ERR_MSG(extack, "Can not change number of buckets of a resilient nexthop group."); return -EINVAL; } /* Emit a pre-replace notification so that listeners could veto * a potentially unsupported configuration. Otherwise, * individual bucket replacement notifications would need to be * vetoed, which is something that should only happen if the * bucket is currently active. */ err = call_nexthop_res_table_notifiers(net, new, extack); if (err) return err; if (cfg->nh_grp_res_has_idle_timer) old_res_table->idle_timer = cfg->nh_grp_res_idle_timer; if (cfg->nh_grp_res_has_unbalanced_timer) old_res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer; replace_nexthop_grp_res(oldg, newg); tmp_table = new_res_table; rcu_assign_pointer(newg->res_table, old_res_table); rcu_assign_pointer(newg->spare->res_table, old_res_table); } /* update parents - used by nexthop code for cleanup */ for (i = 0; i < newg->num_nh; i++) newg->nh_entries[i].nh_parent = old; rcu_assign_pointer(old->nh_grp, newg); /* Make sure concurrent readers are not using 'oldg' anymore. */ synchronize_net(); if (newg->resilient) { rcu_assign_pointer(oldg->res_table, tmp_table); rcu_assign_pointer(oldg->spare->res_table, tmp_table); } for (i = 0; i < oldg->num_nh; i++) oldg->nh_entries[i].nh_parent = new; rcu_assign_pointer(new->nh_grp, oldg); return 0; } static void nh_group_v4_update(struct nh_group *nhg) { struct nh_grp_entry *nhges; bool has_v4 = false; int i; nhges = nhg->nh_entries; for (i = 0; i < nhg->num_nh; i++) { struct nh_info *nhi; nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) has_v4 = true; } nhg->has_v4 = has_v4; } static int replace_nexthop_single_notify_res(struct net *net, struct nh_res_table *res_table, struct nexthop *old, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { u32 nhg_id = res_table->nhg_id; int err; u16 i; for (i = 0; i < res_table->num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; nhge = rtnl_dereference(bucket->nh_entry); if (nhge->nh == old) { err = __call_nexthop_res_bucket_notifiers(net, nhg_id, i, true, oldi, newi, extack); if (err) goto err_notify; } } return 0; err_notify: while (i-- > 0) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; struct nh_grp_entry *nhge; nhge = rtnl_dereference(bucket->nh_entry); if (nhge->nh == old) __call_nexthop_res_bucket_notifiers(net, nhg_id, i, true, newi, oldi, extack); } return err; } static int replace_nexthop_single_notify(struct net *net, struct nexthop *group_nh, struct nexthop *old, struct nh_info *oldi, struct nh_info *newi, struct netlink_ext_ack *extack) { struct nh_group *nhg = rtnl_dereference(group_nh->nh_grp); struct nh_res_table *res_table; if (nhg->hash_threshold) { return call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, group_nh, extack); } else if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); return replace_nexthop_single_notify_res(net, res_table, old, oldi, newi, extack); } return -EINVAL; } static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { u8 old_protocol, old_nh_flags; struct nh_info *oldi, *newi; struct nh_grp_entry *nhge; int err; if (new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group."); return -EINVAL; } err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); if (err) return err; /* Hardware flags were set on 'old' as 'new' is not in the red-black * tree. Therefore, inherit the flags from 'old' to 'new'. */ new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP); oldi = rtnl_dereference(old->nh_info); newi = rtnl_dereference(new->nh_info); newi->nh_parent = old; oldi->nh_parent = new; old_protocol = old->protocol; old_nh_flags = old->nh_flags; old->protocol = new->protocol; old->nh_flags = new->nh_flags; rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); /* Send a replace notification for all the groups using the nexthop. */ list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; err = replace_nexthop_single_notify(net, nhp, old, oldi, newi, extack); if (err) goto err_notify; } /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially * update IPv4 indication in all the groups using the nexthop. */ if (oldi->family == AF_INET && newi->family == AF_INET6) { list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; struct nh_group *nhg; nhg = rtnl_dereference(nhp->nh_grp); nh_group_v4_update(nhg); } } return 0; err_notify: rcu_assign_pointer(new->nh_info, newi); rcu_assign_pointer(old->nh_info, oldi); old->nh_flags = old_nh_flags; old->protocol = old_protocol; oldi->nh_parent = old; newi->nh_parent = new; list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; replace_nexthop_single_notify(net, nhp, old, newi, oldi, NULL); } call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack); return err; } static void __nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct fib6_info *f6i; if (!list_empty(&nh->fi_list)) { struct fib_info *fi; /* expectation is a few fib_info per nexthop and then * a lot of routes per fib_info. So mark the fib_info * and then walk the fib tables once */ list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = true; fib_info_notify_update(net, info); list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = false; } list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_rt_update(net, f6i, info); } /* send RTM_NEWROUTE with REPLACE flag set for all FIB entries * linked to this nexthop and for all groups that the nexthop * is a member of */ static void nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct nh_grp_entry *nhge; __nexthop_replace_notify(net, nh, info); list_for_each_entry(nhge, &nh->grp_list, nh_list) __nexthop_replace_notify(net, nhge->nh_parent, info); } static int replace_nexthop(struct net *net, struct nexthop *old, struct nexthop *new, const struct nh_config *cfg, struct netlink_ext_ack *extack) { bool new_is_reject = false; struct nh_grp_entry *nhge; int err; /* check that existing FIB entries are ok with the * new nexthop definition */ err = fib_check_nh_list(old, new, extack); if (err) return err; err = fib6_check_nh_list(old, new, extack); if (err) return err; if (!new->is_group) { struct nh_info *nhi = rtnl_dereference(new->nh_info); new_is_reject = nhi->reject_nh; } list_for_each_entry(nhge, &old->grp_list, nh_list) { /* if new nexthop is a blackhole, any groups using this * nexthop cannot have more than 1 path */ if (new_is_reject && nexthop_num_path(nhge->nh_parent) > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path"); return -EINVAL; } err = fib_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; err = fib6_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; } if (old->is_group) err = replace_nexthop_grp(net, old, new, cfg, extack); else err = replace_nexthop_single(net, old, new, extack); if (!err) { nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); } return err; } /* called with rtnl_lock held */ static int insert_nexthop(struct net *net, struct nexthop *new_nh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct rb_node **pp, *parent = NULL, *next; struct rb_root *root = &net->nexthop.rb_root; bool replace = !!(cfg->nlflags & NLM_F_REPLACE); bool create = !!(cfg->nlflags & NLM_F_CREATE); u32 new_id = new_nh->id; int replace_notify = 0; int rc = -EEXIST; pp = &root->rb_node; while (1) { struct nexthop *nh; next = *pp; if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (new_id < nh->id) { pp = &next->rb_left; } else if (new_id > nh->id) { pp = &next->rb_right; } else if (replace) { rc = replace_nexthop(net, nh, new_nh, cfg, extack); if (!rc) { new_nh = nh; /* send notification with old nh */ replace_notify = 1; } goto out; } else { /* id already exists and not a replace */ goto out; } } if (replace && !create) { NL_SET_ERR_MSG(extack, "Replace specified without create and no entry exists"); rc = -ENOENT; goto out; } if (new_nh->is_group) { struct nh_group *nhg = rtnl_dereference(new_nh->nh_grp); struct nh_res_table *res_table; if (nhg->resilient) { res_table = rtnl_dereference(nhg->res_table); /* Not passing the number of buckets is OK when * replacing, but not when creating a new group. */ if (!cfg->nh_grp_res_has_num_buckets) { NL_SET_ERR_MSG(extack, "Number of buckets not specified for nexthop group insertion"); rc = -EINVAL; goto out; } nh_res_group_rebalance(nhg, res_table); /* Do not send bucket notifications, we do full * notification below. */ nh_res_table_upkeep(res_table, false, false); } } rb_link_node_rcu(&new_nh->rb_node, parent, pp); rb_insert_color(&new_nh->rb_node, root); /* The initial insertion is a full notification for hash-threshold as * well as resilient groups. */ rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack); if (rc) rb_erase(&new_nh->rb_node, &net->nexthop.rb_root); out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); if (replace_notify && READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } return rc; } /* rtnl */ /* remove all nexthops tied to a device being deleted */ static void nexthop_flush_dev(struct net_device *dev, unsigned long event) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev != dev) continue; if (nhi->reject_nh && (event == NETDEV_DOWN || event == NETDEV_CHANGE)) continue; remove_nexthop(net, nhi->nh_parent, NULL); } } /* rtnl; called when net namespace is deleted */ static void flush_all_nexthops(struct net *net) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; struct nexthop *nh; while ((node = rb_first(root))) { nh = rb_entry(node, struct nexthop, rb_node); remove_nexthop(net, nh, NULL); cond_resched(); } } static struct nexthop *nexthop_create_group(struct net *net, struct nh_config *cfg) { struct nlattr *grps_attr = cfg->nh_grp; struct nexthop_grp *entry = nla_data(grps_attr); u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; int err; int i; if (WARN_ON(!num_nh)) return ERR_PTR(-EINVAL); nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nh->is_group = 1; nhg = nexthop_grp_alloc(num_nh); if (!nhg) { kfree(nh); return ERR_PTR(-ENOMEM); } /* spare group used for removals */ nhg->spare = nexthop_grp_alloc(num_nh); if (!nhg->spare) { kfree(nhg); kfree(nh); return ERR_PTR(-ENOMEM); } nhg->spare->spare = nhg; for (i = 0; i < nhg->num_nh; ++i) { struct nexthop *nhe; struct nh_info *nhi; nhe = nexthop_find_by_id(net, entry[i].id); if (!nexthop_get(nhe)) { err = -ENOENT; goto out_no_nh; } nhi = rtnl_dereference(nhe->nh_info); if (nhi->family == AF_INET) nhg->has_v4 = true; nhg->nh_entries[i].stats = netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); if (!nhg->nh_entries[i].stats) { err = -ENOMEM; nexthop_put(nhe); goto out_no_nh; } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]); list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { nhg->hash_threshold = 1; nhg->is_multipath = true; } else if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) { struct nh_res_table *res_table; res_table = nexthop_res_table_alloc(net, cfg->nh_id, cfg); if (!res_table) { err = -ENOMEM; goto out_no_nh; } rcu_assign_pointer(nhg->spare->res_table, res_table); rcu_assign_pointer(nhg->res_table, res_table); nhg->resilient = true; nhg->is_multipath = true; } WARN_ON_ONCE(nhg->hash_threshold + nhg->resilient != 1); if (nhg->hash_threshold) nh_hthr_group_rebalance(nhg); if (cfg->nh_fdb) nhg->fdb_nh = 1; if (cfg->nh_hw_stats) nhg->hw_stats = true; rcu_assign_pointer(nh->nh_grp, nhg); return nh; out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } kfree(nhg->spare); kfree(nhg); kfree(nh); return ERR_PTR(err); } static int nh_create_ipv4(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib_nh *fib_nh = &nhi->fib_nh; struct fib_config fib_cfg = { .fc_oif = cfg->nh_ifindex, .fc_gw4 = cfg->gw.ipv4, .fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; u32 tb_id = (cfg->dev ? l3mdev_fib_table(cfg->dev) : RT_TABLE_MAIN); int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); if (err) { fib_nh_release(net, fib_nh); goto out; } if (nhi->fdb_nh) goto out; /* sets nh_dev if successful */ err = fib_check_nh(net, fib_nh, tb_id, 0, extack); if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } out: return err; } static int nh_create_ipv6(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib6_nh *fib6_nh = &nhi->fib6_nh; struct fib6_config fib6_cfg = { .fc_table = l3mdev_fib_table(cfg->dev), .fc_ifindex = cfg->nh_ifindex, .fc_gateway = cfg->gw.ipv6, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, .fc_is_fdb = cfg->nh_fdb, }; int err; if (!ipv6_addr_any(&cfg->gw.ipv6)) fib6_cfg.fc_flags |= RTF_GATEWAY; /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); if (err) { /* IPv6 is not enabled, don't call fib6_nh_release */ if (err == -EAFNOSUPPORT) goto out; ipv6_stub->fib6_nh_release(fib6_nh); } else { nh->nh_flags = fib6_nh->fib_nh_flags; } out: return err; } static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; struct nexthop *nh; int err = 0; nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nhi = kzalloc(sizeof(*nhi), GFP_KERNEL); if (!nhi) { kfree(nh); return ERR_PTR(-ENOMEM); } nh->nh_flags = cfg->nh_flags; nh->net = net; nhi->nh_parent = nh; nhi->family = cfg->nh_family; nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; if (cfg->nh_fdb) nhi->fdb_nh = 1; if (cfg->nh_blackhole) { nhi->reject_nh = 1; cfg->nh_ifindex = net->loopback_dev->ifindex; } switch (cfg->nh_family) { case AF_INET: err = nh_create_ipv4(net, nh, nhi, cfg, extack); break; case AF_INET6: err = nh_create_ipv6(net, nh, nhi, cfg, extack); break; } if (err) { kfree(nhi); kfree(nh); return ERR_PTR(err); } /* add the entry to the device based hash */ if (!nhi->fdb_nh) nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); return nh; } /* called with rtnl lock held */ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nexthop *nh; int err; if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) { NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); return ERR_PTR(-EINVAL); } if (!cfg->nh_id) { cfg->nh_id = nh_find_unused_id(net); if (!cfg->nh_id) { NL_SET_ERR_MSG(extack, "No unused id"); return ERR_PTR(-EINVAL); } } if (cfg->nh_grp) nh = nexthop_create_group(net, cfg); else nh = nexthop_create(net, cfg, extack); if (IS_ERR(nh)) return nh; refcount_set(&nh->refcnt, 1); nh->id = cfg->nh_id; nh->protocol = cfg->nh_protocol; nh->net = net; err = insert_nexthop(net, nh, cfg, extack); if (err) { __remove_nexthop(net, nh, NULL); nexthop_put(nh); nh = ERR_PTR(err); } return nh; } static int rtm_nh_get_timer(struct nlattr *attr, unsigned long fallback, unsigned long *timer_p, bool *has_p, struct netlink_ext_ack *extack) { unsigned long timer; u32 value; if (!attr) { *timer_p = fallback; *has_p = false; return 0; } value = nla_get_u32(attr); timer = clock_t_to_jiffies(value); if (timer == ~0UL) { NL_SET_ERR_MSG(extack, "Timer value too large"); return -EINVAL; } *timer_p = timer; *has_p = true; return 0; } static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_policy_new)] = {}; int err; if (res) { err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_policy_new) - 1, res, rtm_nh_res_policy_new, extack); if (err < 0) return err; } if (tb[NHA_RES_GROUP_BUCKETS]) { cfg->nh_grp_res_num_buckets = nla_get_u16(tb[NHA_RES_GROUP_BUCKETS]); cfg->nh_grp_res_has_num_buckets = true; if (!cfg->nh_grp_res_num_buckets) { NL_SET_ERR_MSG(extack, "Number of buckets needs to be non-0"); return -EINVAL; } } err = rtm_nh_get_timer(tb[NHA_RES_GROUP_IDLE_TIMER], NH_RES_DEFAULT_IDLE_TIMER, &cfg->nh_grp_res_idle_timer, &cfg->nh_grp_res_has_idle_timer, extack); if (err) return err; return rtm_nh_get_timer(tb[NHA_RES_GROUP_UNBALANCED_TIMER], NH_RES_DEFAULT_UNBALANCED_TIMER, &cfg->nh_grp_res_unbalanced_timer, &cfg->nh_grp_res_has_unbalanced_timer, extack); } static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; int err; err = nlmsg_parse(nlh, sizeof(*nhm), tb, ARRAY_SIZE(rtm_nh_policy_new) - 1, rtm_nh_policy_new, extack); if (err < 0) return err; err = -EINVAL; if (nhm->resvd || nhm->nh_scope) { NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); goto out; } if (nhm->nh_flags & ~NEXTHOP_VALID_USER_FLAGS) { NL_SET_ERR_MSG(extack, "Invalid nexthop flags in ancillary header"); goto out; } switch (nhm->nh_family) { case AF_INET: case AF_INET6: break; case AF_UNSPEC: if (tb[NHA_GROUP]) break; fallthrough; default: NL_SET_ERR_MSG(extack, "Invalid address family"); goto out; } memset(cfg, 0, sizeof(*cfg)); cfg->nlflags = nlh->nlmsg_flags; cfg->nlinfo.portid = NETLINK_CB(skb).portid; cfg->nlinfo.nlh = nlh; cfg->nlinfo.nl_net = net; cfg->nh_family = nhm->nh_family; cfg->nh_protocol = nhm->nh_protocol; cfg->nh_flags = nhm->nh_flags; if (tb[NHA_ID]) cfg->nh_id = nla_get_u32(tb[NHA_ID]); if (tb[NHA_FDB]) { if (tb[NHA_OIF] || tb[NHA_BLACKHOLE] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "Fdb attribute can not be used with encap, oif or blackhole"); goto out; } if (nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Unsupported nexthop flags in ancillary header"); goto out; } cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]); } if (tb[NHA_GROUP]) { if (nhm->nh_family != AF_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid family for group"); goto out; } cfg->nh_grp = tb[NHA_GROUP]; cfg->nh_grp_type = NEXTHOP_GRP_TYPE_MPATH; if (tb[NHA_GROUP_TYPE]) cfg->nh_grp_type = nla_get_u16(tb[NHA_GROUP_TYPE]); if (cfg->nh_grp_type > NEXTHOP_GRP_TYPE_MAX) { NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), cfg->nh_grp_type, extack); if (err) goto out; if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); if (tb[NHA_HW_STATS_ENABLE]) cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); /* no other attributes should be set */ goto out; } if (tb[NHA_BLACKHOLE]) { if (tb[NHA_GATEWAY] || tb[NHA_OIF] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE] || tb[NHA_FDB]) { NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway, oif, encap or fdb"); goto out; } cfg->nh_blackhole = 1; err = 0; goto out; } if (!cfg->nh_fdb && !tb[NHA_OIF]) { NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole and non-fdb nexthops"); goto out; } if (!cfg->nh_fdb && tb[NHA_OIF]) { cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); if (cfg->nh_ifindex) cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); if (!cfg->dev) { NL_SET_ERR_MSG(extack, "Invalid device index"); goto out; } else if (!(cfg->dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } else if (!netif_carrier_ok(cfg->dev)) { NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); err = -ENETDOWN; goto out; } } err = -EINVAL; if (tb[NHA_GATEWAY]) { struct nlattr *gwa = tb[NHA_GATEWAY]; switch (cfg->nh_family) { case AF_INET: if (nla_len(gwa) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv4 = nla_get_be32(gwa); break; case AF_INET6: if (nla_len(gwa) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv6 = nla_get_in6_addr(gwa); break; default: NL_SET_ERR_MSG(extack, "Unknown address family for gateway"); goto out; } } else { /* device only nexthop (no gateway) */ if (cfg->nh_flags & RTNH_F_ONLINK) { NL_SET_ERR_MSG(extack, "ONLINK flag can not be set for nexthop without a gateway"); goto out; } } if (tb[NHA_ENCAP]) { cfg->nh_encap = tb[NHA_ENCAP]; if (!tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation type is missing"); goto out; } cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack); if (err < 0) goto out; } else if (tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation attribute is missing"); goto out; } if (tb[NHA_HW_STATS_ENABLE]) { NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); goto out; } err = 0; out: return err; } /* rtnl */ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nh_config cfg; struct nexthop *nh; int err; err = rtm_to_nh_config(net, skb, nlh, &cfg, extack); if (!err) { nh = nexthop_add(net, &cfg, extack); if (IS_ERR(nh)) err = PTR_ERR(nh); } return err; } static int nh_valid_get_del_req(const struct nlmsghdr *nlh, struct nlattr **tb, u32 *id, u32 *op_flags, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header"); return -EINVAL; } if (!tb[NHA_ID]) { NL_SET_ERR_MSG(extack, "Nexthop id is missing"); return -EINVAL; } *id = nla_get_u32(tb[NHA_ID]); if (!(*id)) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (op_flags) *op_flags = nla_get_u32_default(tb[NHA_OP_FLAGS], 0); return 0; } /* rtnl */ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_del)]; struct net *net = sock_net(skb->sk); struct nl_info nlinfo = { .nlh = nlh, .nl_net = net, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; int err; u32 id; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_del) - 1, rtm_nh_policy_del, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, &id, NULL, extack); if (err) return err; nh = nexthop_find_by_id(net, id); if (!nh) return -ENOENT; remove_nexthop(net, nh, &nlinfo); return 0; } /* rtnl */ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; struct net *net = sock_net(in_skb->sk); struct sk_buff *skb = NULL; struct nexthop *nh; u32 op_flags; int err; u32 id; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_get) - 1, rtm_nh_policy_get, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto out; err = -ENOENT; nh = nexthop_find_by_id(net, id); if (!nh) goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); out: return err; errout_free: kfree_skb(skb); goto out; } struct nh_dump_filter { u32 nh_id; int dev_idx; int master_idx; bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, struct nh_dump_filter *filter, u8 family) { const struct net_device *dev; const struct nh_info *nhi; if (filter->group_filter && !nh->is_group) return true; if (!filter->dev_idx && !filter->master_idx && !family) return false; if (nh->is_group) return true; nhi = rtnl_dereference(nh->nh_info); if (family && nhi->family != family) return true; dev = nhi->fib_nhc.nhc_dev; if (filter->dev_idx && (!dev || dev->ifindex != filter->dev_idx)) return true; if (filter->master_idx) { struct net_device *master; if (!dev) return true; master = netdev_master_upper_dev_get((struct net_device *)dev); if (!master || master->ifindex != filter->master_idx) return true; } return false; } static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, struct nh_dump_filter *filter, struct netlink_ext_ack *extack) { struct nhmsg *nhm; u32 idx; if (tb[NHA_OIF]) { idx = nla_get_u32(tb[NHA_OIF]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid device index"); return -EINVAL; } filter->dev_idx = idx; } if (tb[NHA_MASTER]) { idx = nla_get_u32(tb[NHA_MASTER]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid master device index"); return -EINVAL; } filter->master_idx = idx; } filter->group_filter = nla_get_flag(tb[NHA_GROUPS]); filter->fdb_filter = nla_get_flag(tb[NHA_FDB]); nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for nexthop dump request"); return -EINVAL; } return 0; } static int nh_valid_dump_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_dump) - 1, rtm_nh_policy_dump, cb->extack); if (err < 0) return err; filter->op_flags = nla_get_u32_default(tb[NHA_OP_FLAGS], 0); return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } struct rtm_dump_nh_ctx { u32 idx; }; static struct rtm_dump_nh_ctx * rtm_dump_nh_ctx(struct netlink_callback *cb) { struct rtm_dump_nh_ctx *ctx = (void *)cb->ctx; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); return ctx; } static int rtm_dump_walk_nexthops(struct sk_buff *skb, struct netlink_callback *cb, struct rb_root *root, struct rtm_dump_nh_ctx *ctx, int (*nh_cb)(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data), void *data) { struct rb_node *node; int s_idx; int err; s_idx = ctx->idx; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); if (nh->id < s_idx) continue; ctx->idx = nh->id; err = nh_cb(skb, cb, nh, data); if (err) return err; } return 0; } static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data) { struct nhmsg *nhm = nlmsg_data(cb->nlh); struct nh_dump_filter *filter = data; if (nh_dump_filtered(nh, filter, nhm->nh_family)) return 0; return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) { struct rtm_dump_nh_ctx *ctx = rtm_dump_nh_ctx(cb); struct net *net = sock_net(skb->sk); struct rb_root *root = &net->nexthop.rb_root; struct nh_dump_filter filter = {}; int err; err = nh_valid_dump_req(cb->nlh, &filter, cb); if (err < 0) return err; err = rtm_dump_walk_nexthops(skb, cb, root, ctx, &rtm_dump_nexthop_cb, &filter); cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static struct nexthop * nexthop_find_group_resilient(struct net *net, u32 id, struct netlink_ext_ack *extack) { struct nh_group *nhg; struct nexthop *nh; nh = nexthop_find_by_id(net, id); if (!nh) return ERR_PTR(-ENOENT); if (!nh->is_group) { NL_SET_ERR_MSG(extack, "Not a nexthop group"); return ERR_PTR(-EINVAL); } nhg = rtnl_dereference(nh->nh_grp); if (!nhg->resilient) { NL_SET_ERR_MSG(extack, "Nexthop group not of type resilient"); return ERR_PTR(-EINVAL); } return nh; } static int nh_valid_dump_nhid(struct nlattr *attr, u32 *nh_id_p, struct netlink_ext_ack *extack) { u32 idx; if (attr) { idx = nla_get_u32(attr); if (!idx) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } *nh_id_p = idx; } else { *nh_id_p = 0; } return 0; } static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { struct nlattr *res_tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_dump)]; struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump_bucket)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_dump_bucket) - 1, rtm_nh_policy_dump_bucket, NULL); if (err < 0) return err; err = nh_valid_dump_nhid(tb[NHA_ID], &filter->nh_id, cb->extack); if (err) return err; if (tb[NHA_RES_BUCKET]) { size_t max = ARRAY_SIZE(rtm_nh_res_bucket_policy_dump) - 1; err = nla_parse_nested(res_tb, max, tb[NHA_RES_BUCKET], rtm_nh_res_bucket_policy_dump, cb->extack); if (err < 0) return err; err = nh_valid_dump_nhid(res_tb[NHA_RES_BUCKET_NH_ID], &filter->res_bucket_nh_id, cb->extack); if (err) return err; } return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } struct rtm_dump_res_bucket_ctx { struct rtm_dump_nh_ctx nh; u16 bucket_index; }; static struct rtm_dump_res_bucket_ctx * rtm_dump_res_bucket_ctx(struct netlink_callback *cb) { struct rtm_dump_res_bucket_ctx *ctx = (void *)cb->ctx; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); return ctx; } struct rtm_dump_nexthop_bucket_data { struct rtm_dump_res_bucket_ctx *ctx; struct nh_dump_filter filter; }; static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, struct rtm_dump_nexthop_bucket_data *dd) { u32 portid = NETLINK_CB(cb->skb).portid; struct nhmsg *nhm = nlmsg_data(cb->nlh); struct nh_res_table *res_table; struct nh_group *nhg; u16 bucket_index; int err; nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); for (bucket_index = dd->ctx->bucket_index; bucket_index < res_table->num_nh_buckets; bucket_index++) { struct nh_res_bucket *bucket; struct nh_grp_entry *nhge; bucket = &res_table->nh_buckets[bucket_index]; nhge = rtnl_dereference(bucket->nh_entry); if (nh_dump_filtered(nhge->nh, &dd->filter, nhm->nh_family)) continue; if (dd->filter.res_bucket_nh_id && dd->filter.res_bucket_nh_id != nhge->nh->id) continue; dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); if (err) return err; } dd->ctx->bucket_index = 0; return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, struct netlink_callback *cb, struct nexthop *nh, void *data) { struct rtm_dump_nexthop_bucket_data *dd = data; struct nh_group *nhg; if (!nh->is_group) return 0; nhg = rtnl_dereference(nh->nh_grp); if (!nhg->resilient) return 0; return rtm_dump_nexthop_bucket_nh(skb, cb, nh, dd); } /* rtnl */ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, struct netlink_callback *cb) { struct rtm_dump_res_bucket_ctx *ctx = rtm_dump_res_bucket_ctx(cb); struct rtm_dump_nexthop_bucket_data dd = { .ctx = ctx }; struct net *net = sock_net(skb->sk); struct nexthop *nh; int err; err = nh_valid_dump_bucket_req(cb->nlh, &dd.filter, cb); if (err) return err; if (dd.filter.nh_id) { nh = nexthop_find_group_resilient(net, dd.filter.nh_id, cb->extack); if (IS_ERR(nh)) return PTR_ERR(nh); err = rtm_dump_nexthop_bucket_nh(skb, cb, nh, &dd); } else { struct rb_root *root = &net->nexthop.rb_root; err = rtm_dump_walk_nexthops(skb, cb, root, &ctx->nh, &rtm_dump_nexthop_bucket_cb, &dd); } cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static int nh_valid_get_bucket_req_res_bucket(struct nlattr *res, u16 *bucket_index, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_get)]; int err; err = nla_parse_nested(tb, ARRAY_SIZE(rtm_nh_res_bucket_policy_get) - 1, res, rtm_nh_res_bucket_policy_get, extack); if (err < 0) return err; if (!tb[NHA_RES_BUCKET_INDEX]) { NL_SET_ERR_MSG(extack, "Bucket index is missing"); return -EINVAL; } *bucket_index = nla_get_u16(tb[NHA_RES_BUCKET_INDEX]); return 0; } static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, u32 *id, u16 *bucket_index, struct netlink_ext_ack *extack) { struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get_bucket)]; int err; err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, ARRAY_SIZE(rtm_nh_policy_get_bucket) - 1, rtm_nh_policy_get_bucket, extack); if (err < 0) return err; err = nh_valid_get_del_req(nlh, tb, id, NULL, extack); if (err) return err; if (!tb[NHA_RES_BUCKET]) { NL_SET_ERR_MSG(extack, "Bucket information is missing"); return -EINVAL; } err = nh_valid_get_bucket_req_res_bucket(tb[NHA_RES_BUCKET], bucket_index, extack); if (err) return err; return 0; } /* rtnl */ static int rtm_get_nexthop_bucket(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nh_res_table *res_table; struct sk_buff *skb = NULL; struct nh_group *nhg; struct nexthop *nh; u16 bucket_index; int err; u32 id; err = nh_valid_get_bucket_req(nlh, &id, &bucket_index, extack); if (err) return err; nh = nexthop_find_group_resilient(net, id, extack); if (IS_ERR(nh)) return PTR_ERR(nh); nhg = rtnl_dereference(nh->nh_grp); res_table = rtnl_dereference(nhg->res_table); if (bucket_index >= res_table->num_nh_buckets) { NL_SET_ERR_MSG(extack, "Bucket index out of bounds"); return -ENOENT; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; err = nh_fill_res_bucket(skb, nh, &res_table->nh_buckets[bucket_index], bucket_index, RTM_NEWNEXTHOPBUCKET, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, extack); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: kfree_skb(skb); return err; } static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev == dev) { if (nhi->family == AF_INET) fib_nhc_update_mtu(&nhi->fib_nhc, dev->mtu, orig_mtu); } } } /* rtnl */ static int nh_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_info_ext *info_ext; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: info_ext = ptr; nexthop_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(dev_net(dev)); break; } return NOTIFY_DONE; } static struct notifier_block nh_netdev_notifier = { .notifier_call = nh_netdev_event, }; static int nexthops_dump(struct net *net, struct notifier_block *nb, enum nexthop_event_type event_type, struct netlink_ext_ack *extack) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; int err = 0; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; nh = rb_entry(node, struct nexthop, rb_node); err = call_nexthop_notifier(nb, net, event_type, nh, extack); if (err) break; } return err; } int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; rtnl_lock(); err = nexthops_dump(net, nb, NEXTHOP_EVENT_REPLACE, extack); if (err) goto unlock; err = blocking_notifier_chain_register(&net->nexthop.notifier_chain, nb); unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(register_nexthop_notifier); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); if (!err) nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); return err; } EXPORT_SYMBOL(__unregister_nexthop_notifier); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __unregister_nexthop_notifier(net, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_nexthop_notifier); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap) { struct nexthop *nexthop; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop) goto out; nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); if (offload) nexthop->nh_flags |= RTNH_F_OFFLOAD; if (trap) nexthop->nh_flags |= RTNH_F_TRAP; out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_set_hw_flags); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap) { struct nh_res_table *res_table; struct nh_res_bucket *bucket; struct nexthop *nexthop; struct nh_group *nhg; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop || !nexthop->is_group) goto out; nhg = rcu_dereference(nexthop->nh_grp); if (!nhg->resilient) goto out; if (bucket_index >= nhg->res_table->num_nh_buckets) goto out; res_table = rcu_dereference(nhg->res_table); bucket = &res_table->nh_buckets[bucket_index]; bucket->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); if (offload) bucket->nh_flags |= RTNH_F_OFFLOAD; if (trap) bucket->nh_flags |= RTNH_F_TRAP; out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_bucket_set_hw_flags); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity) { struct nh_res_table *res_table; struct nexthop *nexthop; struct nh_group *nhg; u16 i; rcu_read_lock(); nexthop = nexthop_find_by_id(net, id); if (!nexthop || !nexthop->is_group) goto out; nhg = rcu_dereference(nexthop->nh_grp); if (!nhg->resilient) goto out; /* Instead of silently ignoring some buckets, demand that the sizes * be the same. */ res_table = rcu_dereference(nhg->res_table); if (num_buckets != res_table->num_nh_buckets) goto out; for (i = 0; i < num_buckets; i++) { if (test_bit(i, activity)) nh_res_bucket_set_busy(&res_table->nh_buckets[i]); } out: rcu_read_unlock(); } EXPORT_SYMBOL(nexthop_res_grp_activity_update); static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) flush_all_nexthops(net); } static void __net_exit nexthop_net_exit(struct net *net) { kfree(net->nexthop.devhash); net->nexthop.devhash = NULL; } static int __net_init nexthop_net_init(struct net *net) { size_t sz = sizeof(struct hlist_head) * NH_DEV_HASHSIZE; net->nexthop.rb_root = RB_ROOT; net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); if (!net->nexthop.devhash) return -ENOMEM; BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); return 0; } static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, .exit = nexthop_net_exit, .exit_batch_rtnl = nexthop_net_exit_batch_rtnl, }; static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop}, {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop}, {.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop, .dumpit = rtm_dump_nexthop}, {.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket, .dumpit = rtm_dump_nexthop_bucket}, {.protocol = PF_INET, .msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop}, {.protocol = PF_INET, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, {.protocol = PF_INET6, .msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop}, {.protocol = PF_INET6, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, }; static int __init nexthop_init(void) { register_pernet_subsys(&nexthop_net_ops); register_netdevice_notifier(&nh_netdev_notifier); rtnl_register_many(nexthop_rtnl_msg_handlers); return 0; } subsys_initcall(nexthop_init); |
| 346 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif #define PERF_GUEST_ACTIVE 0x01 #define PERF_GUEST_USER 0x02 struct perf_guest_info_callbacks { unsigned int (*state)(void); unsigned long (*get_ip)(void); unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <linux/rhashtable-types.h> #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> #include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * hw_perf_event::flag values * * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ #define PERF_EVENT_FLAG_ARCH 0x000fffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* aux / Intel-PT */ u64 aux_config; /* * For AUX area events, aux_paused cannot be a state * flag because it can be updated asynchronously to * state. */ unsigned int aux_paused; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; struct perf_event_pmu_context; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x0001 #define PERF_PMU_CAP_NO_NMI 0x0002 #define PERF_PMU_CAP_AUX_NO_SG 0x0004 #define PERF_PMU_CAP_EXTENDED_REGS 0x0008 #define PERF_PMU_CAP_EXCLUSIVE 0x0010 #define PERF_PMU_CAP_ITRACE 0x0020 #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 #define PERF_PMU_CAP_AUX_PAUSE 0x0200 /** * pmu::scope */ enum perf_pmu_scope { PERF_PMU_SCOPE_NONE = 0, PERF_PMU_SCOPE_CORE, PERF_PMU_SCOPE_DIE, PERF_PMU_SCOPE_CLUSTER, PERF_PMU_SCOPE_PKG, PERF_PMU_SCOPE_SYS_WIDE, PERF_PMU_MAX_SCOPE, }; struct perf_output_handle; #define PMU_NULL_DEV ((void *)(~0UL)) /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; struct device *parent; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; /* * PMU scope */ unsigned int scope; int __percpu *pmu_disable_count; struct perf_cpu_pmu_context __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ #define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */ #define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. * * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with * PERF_EF_RESUME. * * ->start() with PERF_EF_RESUME will start as simply as possible but * only if the counter is not otherwise stopped. Will not overlap * another ->start() with PERF_EF_RESUME nor ->stop() with * PERF_EF_PAUSE. * * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to 0 (see * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_pmu_context *prev_epc, struct perf_event_pmu_context *next_epc); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Skip programming this PMU on the given CPU. Typically needed for * big.LITTLE things. */ bool (*filter) (struct pmu *pmu, int cpu); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the * PMU scope where it is active. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define PERF_EV_CAP_READ_SCOPE BIT(3) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 struct bpf_prog; struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; /* * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex * as such iteration must hold either lock. However, since ctx->lock is an IRQ * safe lock, and is only held by the CPU doing the modification, having IRQs * disabled is sufficient since it will hold-off the IPIs. */ #ifdef CONFIG_PROVE_LOCKING #define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) #else #define lockdep_assert_event_ctx(event) #endif #define for_each_sibling_event(sibling, event) \ lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. * Whereas event->pmu_ctx->pmu may point to other pmu when group of * different pmu events is created. */ struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event * is added. This pmu_ctx can be of other pmu for sw event when that * sw event is part of a group which also contains non-sw events. */ struct perf_event_pmu_context *pmu_ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; struct rcuwait pending_work_wait; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; struct bpf_prog *prog; u64 bpf_cookie; #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; /* * Certain events gets forwarded to another pmu internally by over- * writing kernel copy of event->attr.type without user being aware * of it. event->orig_type contains original 'type' requested by * user. */ __u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; /* * ,-----------------------[1:n]------------------------. * V V * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event * | | * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed * (similar to perf_event_context). Locking is as if it were a member of * perf_event_context; specifically: * * modification, both: ctx->mutex && ctx->lock * reading, either: ctx->mutex || ctx->lock * * There is one exception to this; namely put_pmu_ctx() isn't always called * with ctx->mutex held; this means that as long as we can guarantee the epc * has events the above rules hold. * * Specificially, sys_perf_event_open()'s group_leader case depends on * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. * * perf_event holds a refcount on perf_event_context * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; struct perf_event_context *ctx; struct list_head pmu_ctx_entry; struct list_head pinned_active; struct list_head flexible_active; /* Used to avoid freeing per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; unsigned int nr_cgroups; unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; void *task_ctx_data; /* pmu specific data */ /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to * events not necessary to be active due to scheduling constraints, * such as cgroups. */ int rotate_necessary; }; static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) { return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); } struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head pmu_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; int nr_events; int nr_user; int is_active; int nr_task_data; int nr_stat; int nr_freq; int rotate_disable; refcount_t refcount; /* event <-> ctx */ struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif struct rcu_head rcu_head; /* * The count of events for which using the switch-out fast path * should be avoided. * * Sum (event->pending_work + events with * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_no_switch_fast; }; struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; struct list_head sched_cb_entry; int sched_cb_usage; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; }; /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int online; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; #endif /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern struct perf_event_context *perf_cpu_task_ctx(void); extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child, u64 clone_flags); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); static inline bool branch_sample_no_flags(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; } static inline bool branch_sample_no_cycles(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; } static inline bool branch_sample_type(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; } static inline bool branch_sample_hw_index(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; } static inline bool branch_sample_priv(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; } static inline bool branch_sample_counters(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS; } static inline bool branch_sample_call_stack(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } struct perf_sample_data { /* * Fields set by perf_sample_data_init() unconditionally, * group so as to minimize the cachelines touched. */ u64 sample_flags; u64 period; u64 dyn_size; /* * Fields commonly set by __perf_event_header__init_id(), * group so as to minimize the cachelines touched. */ u64 type; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; struct { u32 cpu; u32 reserved; } cpu_entry; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 ip; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 stream_id; u64 cgroup; u64 addr; u64 phys_addr; u64 data_page_size; u64 code_page_size; u64 aux_size; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA) |\ PERF_MEM_S(LVLNUM, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; data->dyn_size = 0; if (addr) { data->addr = addr; data->sample_flags |= PERF_SAMPLE_ADDR; } } static inline void perf_sample_save_callchain(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs) { int size = 1; if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) return; data->callchain = perf_callchain(event, regs); size += data->callchain->nr; data->dyn_size += size * sizeof(u64); data->sample_flags |= PERF_SAMPLE_CALLCHAIN; } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, struct perf_event *event, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) return; do { sum += frag->size; if (perf_raw_frag_last(frag)) break; frag = frag->next; } while (1); size = round_up(sum + sizeof(u32), sizeof(u64)); raw->size = size - sizeof(u32); frag->pad = raw->size - sum; data->raw = raw; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_RAW; } static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, u64 *brs_cntr) { int size = sizeof(u64); /* nr */ if (!has_branch_stack(event)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) return; if (branch_sample_hw_index(event)) size += sizeof(u64); size += brs->nr * sizeof(struct perf_branch_entry); /* * The extension space for counters is appended after the * struct perf_branch_stack. It is used to store the occurrences * of events of each branch. */ if (brs_cntr) size += brs->nr * sizeof(u64); data->br_stack = brs; data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } static inline u32 perf_sample_data_size(struct perf_sample_data *data, struct perf_event *event) { u32 size = sizeof(struct perf_event_header); size += event->header_size + event->id_header_size; size += data->dyn_size; return size; } /* * Clear all bitfields in the perf_branch_entry. * The to and from fields are not cleared because they are * systematically modified by caller. */ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) { br->mispred = 0; br->predicted = 0; br->in_tx = 0; br->abort = 0; br->cycles = 0; br->type = 0; br->spec = PERF_BR_SPEC_NA; br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern void perf_prepare_header(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { perf_overflow_handler_t overflow_handler = event->overflow_handler; if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } extern struct static_key_false perf_sched_events; static __always_inline bool __perf_sw_enabled(int swevt) { return static_key_false(&perf_swevent_enabled[swevt]); } static inline void perf_event_task_migrate(struct task_struct *task) { if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); #ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); #endif if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); #ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); static inline unsigned int perf_guest_state(void) { return static_call(__perf_guest_state)(); } static inline unsigned long perf_guest_get_ip(void) { return static_call(__perf_guest_get_ip)(); } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return static_call(__perf_guest_handle_intel_pt_intr)(); } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); #else static inline unsigned int perf_guest_state(void) { return 0; } static inline unsigned long perf_guest_get_ip(void) { return 0; } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } #endif /* CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } int perf_allow_kernel(struct perf_event_attr *attr); static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs); extern unsigned long perf_instruction_pointer(struct perf_event *event, struct pt_regs *regs); #ifndef perf_arch_misc_flags # define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_arch_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif #ifndef perf_arch_guest_misc_flags static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) { unsigned long guest_state = perf_guest_state(); if (!(guest_state & PERF_GUEST_ACTIVE)) return 0; if (guest_state & PERF_GUEST_USER) return PERF_RECORD_MISC_GUEST_USER; else return PERF_RECORD_MISC_GUEST_KERNEL; } # define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) #endif static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool has_aux_action(struct perf_event *event) { return event->attr.aux_sample_size || event->attr.aux_pause || event->attr.aux_resume; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) { /* Only the parent has fasync state */ if (event->parent) event = event->parent; return &event->fasync; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr) #define PMU_FORMAT_ATTR_SHOW(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ #define PMU_FORMAT_ATTR(_name, _format) \ PMU_FORMAT_ATTR_SHOW(_name, _format) \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); /* * Snapshot branch stack on software events. * * Branch stack can be very useful in understanding software events. For * example, when a long function, e.g. sys_perf_event_open, returns an * errno, it is not obvious why the function failed. Branch stack could * provide very helpful information in this type of scenarios. * * On software event, it is necessary to stop the hardware branch recorder * fast. Otherwise, the hardware register/buffer will be flushed with * entries of the triggering event. Therefore, static call is used to * stop the hardware recorder. */ /* * cnt is the number of entries allocated for entries. * Return number of entries copied to . */ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); #ifndef PERF_NEEDS_LOPWR_CB static inline void perf_lopwr_cb(bool mode) { } #endif #endif /* _LINUX_PERF_EVENT_H */ |
| 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner * * NOHZ implementation for low and high resolution timers * * Started by: Thomas Gleixner and Ingo Molnar */ #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/percpu.h> #include <linux/nmi.h> #include <linux/profile.h> #include <linux/sched/signal.h> #include <linux/sched/clock.h> #include <linux/sched/stat.h> #include <linux/sched/nohz.h> #include <linux/sched/loadavg.h> #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> #include <linux/context_tracking.h> #include <linux/mm.h> #include <asm/irq_regs.h> #include "tick-internal.h" #include <trace/events/timer.h> /* * Per-CPU nohz control structure */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } /* * The time when the last jiffy update happened. Write access must hold * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a * consistent view of jiffies and last_jiffies_update. */ static ktime_t last_jiffies_update; /* * Must be called with interrupts disabled ! */ static void tick_do_update_jiffies64(ktime_t now) { unsigned long ticks = 1; ktime_t delta, nextp; /* * 64-bit can do a quick check without holding the jiffies lock and * without looking at the sequence count. The smp_load_acquire() * pairs with the update done later in this function. * * 32-bit cannot do that because the store of 'tick_next_period' * consists of two 32-bit stores, and the first store could be * moved by the CPU to a random point in the future. */ if (IS_ENABLED(CONFIG_64BIT)) { if (ktime_before(now, smp_load_acquire(&tick_next_period))) return; } else { unsigned int seq; /* * Avoid contention on 'jiffies_lock' and protect the quick * check with the sequence count. */ do { seq = read_seqcount_begin(&jiffies_seq); nextp = tick_next_period; } while (read_seqcount_retry(&jiffies_seq, seq)); if (ktime_before(now, nextp)) return; } /* Quick check failed, i.e. update is required. */ raw_spin_lock(&jiffies_lock); /* * Re-evaluate with the lock held. Another CPU might have done the * update already. */ if (ktime_before(now, tick_next_period)) { raw_spin_unlock(&jiffies_lock); return; } write_seqcount_begin(&jiffies_seq); delta = ktime_sub(now, tick_next_period); if (unlikely(delta >= TICK_NSEC)) { /* Slow path for long idle sleep times */ s64 incr = TICK_NSEC; ticks += ktime_divns(delta, incr); last_jiffies_update = ktime_add_ns(last_jiffies_update, incr * ticks); } else { last_jiffies_update = ktime_add_ns(last_jiffies_update, TICK_NSEC); } /* Advance jiffies to complete the 'jiffies_seq' protected job */ jiffies_64 += ticks; /* Keep the tick_next_period variable up to date */ nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC); if (IS_ENABLED(CONFIG_64BIT)) { /* * Pairs with smp_load_acquire() in the lockless quick * check above, and ensures that the update to 'jiffies_64' is * not reordered vs. the store to 'tick_next_period', neither * by the compiler nor by the CPU. */ smp_store_release(&tick_next_period, nextp); } else { /* * A plain store is good enough on 32-bit, as the quick check * above is protected by the sequence count. */ tick_next_period = nextp; } /* * Release the sequence count. calc_global_load() below is not * protected by it, but 'jiffies_lock' needs to be held to prevent * concurrent invocations. */ write_seqcount_end(&jiffies_seq); calc_global_load(); raw_spin_unlock(&jiffies_lock); update_wall_time(); } /* * Initialize and return retrieve the jiffies update. */ static ktime_t tick_init_jiffy_update(void) { ktime_t period; raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Have we started the jiffies update yet ? */ if (last_jiffies_update == 0) { u32 rem; /* * Ensure that the tick is aligned to a multiple of * TICK_NSEC. */ div_u64_rem(tick_next_period, TICK_NSEC, &rem); if (rem) tick_next_period += TICK_NSEC - rem; last_jiffies_update = tick_next_period; } period = last_jiffies_update; write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); return period; } static inline int tick_sched_flag_test(struct tick_sched *ts, unsigned long flag) { return !!(ts->flags & flag); } static inline void tick_sched_flag_set(struct tick_sched *ts, unsigned long flag) { lockdep_assert_irqs_disabled(); ts->flags |= flag; } static inline void tick_sched_flag_clear(struct tick_sched *ts, unsigned long flag) { lockdep_assert_irqs_disabled(); ts->flags &= ~flag; } #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int tick_cpu, cpu = smp_processor_id(); /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * 'jiffies_lock'. * * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ tick_cpu = READ_ONCE(tick_do_timer_cpu); if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif WRITE_ONCE(tick_do_timer_cpu, cpu); tick_cpu = cpu; } /* Check if jiffies need an update */ if (tick_cpu == cpu) tick_do_update_jiffies64(now); /* * If the jiffies update stalled for too long (timekeeper in stop_machine() * or VMEXIT'ed for several msecs), force an update. */ if (ts->last_tick_jiffies != jiffies) { ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } else { if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) { tick_do_update_jiffies64(now); ts->stalled_jiffies = 0; ts->last_tick_jiffies = READ_ONCE(jiffies); } } if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long * time. This happens on completely idle SMP systems while * waiting on the login prompt. We also increment the "start of * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too many ticks. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; /* * In case the current tick fired too early past its expected * expiration, make sure we don't bypass the next clock reprogramming * to the same deadline. */ ts->next_tick = 0; } update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } /* * We rearm the timer until we get disabled by the idle code. * Called with interrupts disabled. */ static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer) { struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer); struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); tick_sched_do_timer(ts, now); /* * Do not call when we are not in IRQ context and have * no valid 'regs' pointer */ if (regs) tick_sched_handle(ts, regs); else ts->next_tick = 0; /* * In dynticks mode, tick reprogram is deferred: * - to the idle task if in dynticks-idle * - to IRQ exit if in full-dynticks. */ if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED))) return HRTIMER_NORESTART; hrtimer_forward(timer, now, TICK_NSEC); return HRTIMER_RESTART; } #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; EXPORT_SYMBOL_GPL(tick_nohz_full_mask); bool tick_nohz_full_running; EXPORT_SYMBOL_GPL(tick_nohz_full_running); static atomic_t tick_dep_mask; static bool check_tick_dependency(atomic_t *dep) { int val = atomic_read(dep); if (val & TICK_DEP_MASK_POSIX_TIMER) { trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); return true; } if (val & TICK_DEP_MASK_PERF_EVENTS) { trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); return true; } if (val & TICK_DEP_MASK_SCHED) { trace_tick_stop(0, TICK_DEP_MASK_SCHED); return true; } if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) { trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); return true; } if (val & TICK_DEP_MASK_RCU) { trace_tick_stop(0, TICK_DEP_MASK_RCU); return true; } if (val & TICK_DEP_MASK_RCU_EXP) { trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP); return true; } return false; } static bool can_stop_full_tick(int cpu, struct tick_sched *ts) { lockdep_assert_irqs_disabled(); if (unlikely(!cpu_online(cpu))) return false; if (check_tick_dependency(&tick_dep_mask)) return false; if (check_tick_dependency(&ts->tick_dep_mask)) return false; if (check_tick_dependency(¤t->tick_dep_mask)) return false; if (check_tick_dependency(¤t->signal->tick_dep_mask)) return false; return true; } static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = IRQ_WORK_INIT_HARD(nohz_full_kick_func); /* * Kick this CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; irq_work_queue(this_cpu_ptr(&nohz_full_kick_work)); } /* * Kick the CPU if it's full dynticks in order to force it to * re-evaluate its dependency on the tick and restart it if necessary. */ void tick_nohz_full_kick_cpu(int cpu) { if (!tick_nohz_full_cpu(cpu)) return; irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } static void tick_nohz_kick_task(struct task_struct *tsk) { int cpu; /* * If the task is not running, run_posix_cpu_timers() * has nothing to elapse, and an IPI can then be optimized out. * * activate_task() STORE p->tick_dep_mask * STORE p->on_rq * __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or()) * LOCK rq->lock LOAD p->on_rq * smp_mb__after_spin_lock() * tick_nohz_task_switch() * LOAD p->tick_dep_mask * * XXX given a task picks up the dependency on schedule(), should we * only care about tasks that are currently on the CPU instead of all * that are on the runqueue? * * That is, does this want to be: task_on_cpu() / task_curr()? */ if (!sched_task_on_rq(tsk)) return; /* * If the task concurrently migrates to another CPU, * we guarantee it sees the new tick dependency upon * schedule. * * set_task_cpu(p, cpu); * STORE p->cpu = @cpu * __schedule() (switch to task 'p') * LOCK rq->lock * smp_mb__after_spin_lock() STORE p->tick_dep_mask * tick_nohz_task_switch() smp_mb() (atomic_fetch_or()) * LOAD p->tick_dep_mask LOAD p->cpu */ cpu = task_cpu(tsk); preempt_disable(); if (cpu_online(cpu)) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ static void tick_nohz_full_kick_all(void) { int cpu; if (!tick_nohz_full_running) return; preempt_disable(); for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) tick_nohz_full_kick_cpu(cpu); preempt_enable(); } static void tick_nohz_dep_set_all(atomic_t *dep, enum tick_dep_bits bit) { int prev; prev = atomic_fetch_or(BIT(bit), dep); if (!prev) tick_nohz_full_kick_all(); } /* * Set a global tick dependency. Used by perf events that rely on freq and * unstable clocks. */ void tick_nohz_dep_set(enum tick_dep_bits bit) { tick_nohz_dep_set_all(&tick_dep_mask, bit); } void tick_nohz_dep_clear(enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tick_dep_mask); } /* * Set per-CPU tick dependency. Used by scheduler and perf events in order to * manage event-throttling. */ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { int prev; struct tick_sched *ts; ts = per_cpu_ptr(&tick_cpu_sched, cpu); prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask); if (!prev) { preempt_disable(); /* Perf needs local kick that is NMI safe */ if (cpu == smp_processor_id()) { tick_nohz_full_kick(); } else { /* Remote IRQ work not NMI-safe */ if (!WARN_ON_ONCE(in_nmi())) tick_nohz_full_kick_cpu(cpu); } preempt_enable(); } } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); atomic_andnot(BIT(bit), &ts->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. RCU needs this. Also posix CPU timers * in order to elapse per task timers. */ void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) tick_nohz_kick_task(tsk); } EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task); void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &tsk->tick_dep_mask); } EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task); /* * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse * per process timers. */ void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { int prev; struct signal_struct *sig = tsk->signal; prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask); if (!prev) { struct task_struct *t; lockdep_assert_held(&tsk->sighand->siglock); __for_each_thread(sig, t) tick_nohz_kick_task(t); } } void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) { atomic_andnot(BIT(bit), &sig->tick_dep_mask); } /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: * perf events, posix CPU timers, ... */ void __tick_nohz_task_switch(void) { struct tick_sched *ts; if (!tick_nohz_full_cpu(smp_processor_id())) return; ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); } } /* Get the boot-time nohz CPU list from the kernel parameters. */ void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; } bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { /* * The 'tick_do_timer_cpu' CPU handles housekeeping duty (unbound * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu) return false; return true; } static int tick_nohz_cpu_down(unsigned int cpu) { return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY; } void __init tick_nohz_init(void) { int cpu, ret; if (!tick_nohz_full_running) return; /* * Full dynticks uses IRQ work to drive the tick rescheduling on safe * locking contexts. But then we need IRQ work to raise its own * interrupts to avoid circular dependency on the tick. */ if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support IRQ work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); tick_nohz_full_running = false; return; } if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { cpu = smp_processor_id(); if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { pr_warn("NO_HZ: Clearing %d from nohz_full range " "for timekeeping\n", cpu); cpumask_clear_cpu(cpu, tick_nohz_full_mask); } } for_each_cpu(cpu, tick_nohz_full_mask) ct_cpu_track_user(cpu); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "kernel/nohz:predown", NULL, tick_nohz_cpu_down); WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } #endif /* #ifdef CONFIG_NO_HZ_FULL */ /* * NOHZ - aka dynamic tick functionality */ #ifdef CONFIG_NO_HZ_COMMON /* * NO HZ enabled ? */ bool tick_nohz_enabled __read_mostly = true; unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ static int __init setup_tick_nohz(char *str) { return (kstrtobool(str, &tick_nohz_enabled) == 0); } __setup("nohz=", setup_tick_nohz); bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } /** * tick_nohz_update_jiffies - update jiffies when idle was interrupted * @now: current ktime_t * * Called from interrupt entry when the CPU was idle * * In case the sched_tick was stopped on this CPU, we have to check if jiffies * must be updated. Otherwise an interrupt handler could use a stale jiffy * value. We do this unconditionally on any CPU, as we don't know whether the * CPU, which has the update task assigned, is in a long sleep. */ static void tick_nohz_update_jiffies(ktime_t now) { unsigned long flags; __this_cpu_write(tick_cpu_sched.idle_waketime, now); local_irq_save(flags); tick_do_update_jiffies64(now); local_irq_restore(flags); touch_softlockup_watchdog_sched(); } static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { ktime_t delta; if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))) return; delta = ktime_sub(now, ts->idle_entrytime); write_seqcount_begin(&ts->idle_sleeptime_seq); if (nr_iowait_cpu(smp_processor_id()) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); else ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_wakeup_event(); } static void tick_nohz_start_idle(struct tick_sched *ts) { write_seqcount_begin(&ts->idle_sleeptime_seq); ts->idle_entrytime = ktime_get(); tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_sleep_event(); } static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, bool compute_delta, u64 *last_update_time) { ktime_t now, idle; unsigned int seq; if (!tick_nohz_active) return -1; now = ktime_get(); if (last_update_time) *last_update_time = ktime_to_us(now); do { seq = read_seqcount_begin(&ts->idle_sleeptime_seq); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(*sleeptime, delta); } else { idle = *sleeptime; } } while (read_seqcount_retry(&ts->idle_sleeptime_seq, seq)); return ktime_to_us(idle); } /** * get_cpu_idle_time_us - get the total idle time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative idle time (since boot) for a given * CPU, in microseconds. Note that this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu */ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime, !nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_idle_time_us); /** * get_cpu_iowait_time_us - get the total iowait time of a CPU * @cpu: CPU number to query * @last_update_time: variable to store update time in. Do not update * counters if NULL. * * Return the cumulative iowait time (since boot) for a given * CPU, in microseconds. Note this is partially broken due to * the counter of iowait tasks that can be remotely updated without * any synchronization. Therefore it is possible to observe backward * values within two consecutive reads. * * This time is measured via accounting rather than sampling, * and is as accurate as ktime_get() is. * * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu */ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime, nr_iowait_cpu(cpu), last_update_time); } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); hrtimer_set_expires(&ts->sched_timer, ts->last_tick); /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); } else { tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } /* * Reset to make sure the next tick stop doesn't get fooled by past * cached clock deadline. */ ts->next_tick = 0; } static inline bool local_timer_softirq_pending(void) { return local_timers_pending() & BIT(TIMER_SOFTIRQ); } /* * Read jiffies and the time when jiffies were updated last */ u64 get_jiffies_update(unsigned long *basej) { unsigned long basejiff; unsigned int seq; u64 basemono; do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); *basej = basejiff; return basemono; } /** * tick_nohz_next_event() - return the clock monotonic based next event * @ts: pointer to tick_sched struct * @cpu: CPU number * * Return: * *%0 - When the next event is a maximum of TICK_NSEC in the future * and the tick is not stopped yet * *%next_event - Next event based on clock monotonic */ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, delta, expires; unsigned long basejiff; int tick_cpu; basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work * requests it. * Aside of that, check whether the local timer softirq is * pending. If so, its a bad idea to call get_next_timer_interrupt(), * because there is an already expired timer, so it will request * immediate expiry, which rearms the hardware timer with a * minimal delta, which brings us back to this place * immediately. Lather, rinse and repeat... */ if (rcu_needs_cpu() || arch_needs_cpu() || irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* * Get the next pending timer. If high resolution * timers are enabled this only takes the timer wheel * timers into account. If high resolution timers are * disabled this also looks at the next expiring * hrtimer. */ next_tick = get_next_timer_interrupt(basejiff, basemono); ts->next_timer = next_tick; } /* Make sure next_tick is never before basemono! */ if (WARN_ON_ONCE(basemono > next_tick)) next_tick = basemono; /* * If the tick is due in the next period, keep it ticking or * force prod the timer. */ delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->timer_expires = 0; goto out; } } /* * If this CPU is the one which had the do_timer() duty last, we limit * the sleep time to the timekeeping 'max_deferment' value. * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); tick_cpu = READ_ONCE(tick_do_timer_cpu); if (tick_cpu != cpu && (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta; else expires = KTIME_MAX; ts->timer_expires = min_t(u64, expires, next_tick); out: return ts->timer_expires; } static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); int tick_cpu; u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* * Now the tick should be stopped definitely - so the timer base needs * to be marked idle as well to not miss a newly queued timer. */ expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle); if (expires > ts->timer_expires) { /* * This path could only happen when the first timer was removed * between calculating the possible sleep length and now (when * high resolution mode is not active, timer could also be a * hrtimer). * * We have to stick to the original calculated expiry value to * not stop the tick for too long with a shallow C-state (which * was programmed by cpuidle because of an early next expiration * value). */ expires = ts->timer_expires; } /* If the timer base is not idle, retain the not yet stopped tick. */ if (!timer_idle) return; /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we * don't drop this here, the jiffies might be stale and * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ tick_cpu = READ_ONCE(tick_do_timer_cpu); if (tick_cpu == cpu) { WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE); tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); } else if (tick_cpu != TICK_DO_TIMER_NONE) { tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } /* Skip reprogram of event if it's not changed */ if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; WARN_ONCE(1, "basemono: %llu ts->next_tick: %llu dev->next_event: %llu " "timer->active: %d timer->expires: %llu\n", basemono, ts->next_tick, dev->next_event, hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer)); } /* * tick_nohz_stop_tick() can be called several times before * tick_nohz_restart_sched_tick() is called. This happens when * interrupts arrive which do not cause a reschedule. In the first * call we save the current tick time, so we can restart the * scheduler tick in tick_nohz_restart_sched_tick(). */ if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); tick_sched_flag_set(ts, TS_FLAG_STOPPED); trace_tick_stop(1, TICK_DEP_MASK_NONE); } ts->next_tick = expires; /* * If the expiration time == KTIME_MAX, then we simply stop * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) hrtimer_cancel(&ts->sched_timer); else tick_program_event(KTIME_MAX, 1); return; } if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { hrtimer_set_expires(&ts->sched_timer, expires); tick_program_event(expires, 1); } } static void tick_nohz_retain_tick(struct tick_sched *ts) { ts->timer_expires_base = 0; } #ifdef CONFIG_NO_HZ_FULL static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); else tick_nohz_retain_tick(ts); } #endif /* CONFIG_NO_HZ_FULL */ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ tick_do_update_jiffies64(now); /* * Clear the timer idle flag, so we avoid IPIs on remote queueing and * the clock forward checks in the enqueue path: */ timer_clear_idle(); calc_load_nohz_stop(); touch_softlockup_watchdog_sched(); /* Cancel the scheduled timer and restore the tick: */ tick_sched_flag_clear(ts, TS_FLAG_STOPPED); tick_nohz_restart(ts, now); } static void __tick_nohz_full_update_tick(struct tick_sched *ts, ktime_t now) { #ifdef CONFIG_NO_HZ_FULL int cpu = smp_processor_id(); if (can_stop_full_tick(cpu, ts)) tick_nohz_full_stop_tick(ts, cpu); else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_restart_sched_tick(ts, now); #endif } static void tick_nohz_full_update_tick(struct tick_sched *ts) { if (!tick_nohz_full_cpu(smp_processor_id())) return; if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return; __tick_nohz_full_update_tick(ts, ktime_get()); } /* * A pending softirq outside an IRQ (or softirq disabled section) context * should be waiting for ksoftirqd to handle it. Therefore we shouldn't * reach this code due to the need_resched() early check in can_stop_idle_tick(). * * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the * cpu_down() process, softirqs can still be raised while ksoftirqd is parked, * triggering the code below, since wakep_softirqd() is ignored. * */ static bool report_idle_softirq(void) { static int ratelimit; unsigned int pending = local_softirq_pending(); if (likely(!pending)) return false; /* Some softirqs claim to be safe against hotplug and ksoftirqd parking */ if (!cpu_active(smp_processor_id())) { pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK; if (!pending) return false; } if (ratelimit >= 10) return false; /* On RT, softirq handling may be waiting on some lock */ if (local_bh_blocked()) return false; pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", pending); ratelimit++; return true; } static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { WARN_ON_ONCE(cpu_is_offline(cpu)); if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ))) return false; if (need_resched()) return false; if (unlikely(report_idle_softirq())) return false; if (tick_nohz_full_enabled()) { int tick_cpu = READ_ONCE(tick_do_timer_cpu); /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ if (tick_cpu == cpu) return false; /* Should not happen for nohz-full */ if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE)) return false; } return true; } /** * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick */ void tick_nohz_idle_stop_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); ktime_t expires; /* * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the * tick timer expiration time is known already. */ if (ts->timer_expires_base) expires = ts->timer_expires; else if (can_stop_idle_tick(cpu, ts)) expires = tick_nohz_next_event(ts, cpu); else return; ts->idle_calls++; if (expires > 0LL) { int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } } else { tick_nohz_retain_tick(ts); } } void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); } /** * tick_nohz_idle_enter - prepare for entering idle on the current CPU * * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { struct tick_sched *ts; lockdep_assert_irqs_enabled(); local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_set(ts, TS_FLAG_INIDLE); tick_nohz_start_idle(ts); local_irq_enable(); } /** * tick_nohz_irq_exit - Notify the tick about IRQ exit * * A timer may have been added/modified/deleted either by the current IRQ, * or by another place using this IRQ as a notification. This IRQ may have * also updated the RCU callback list. These events may require a * re-evaluation of the next tick. Depending on the context: * * 1) If the CPU is idle and no resched is pending, just proceed with idle * time accounting. The next tick will be re-evaluated on the next idle * loop iteration. * * 2) If the CPU is nohz_full: * * 2.1) If there is any tick dependency, restart the tick if stopped. * * 2.2) If there is no tick dependency, (re-)evaluate the next tick and * stop/update it accordingly. */ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** * tick_nohz_idle_got_tick - Check whether or not the tick handler has run * * Return: %true if the tick handler has run, otherwise %false */ bool tick_nohz_idle_got_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->got_idle_tick) { ts->got_idle_tick = 0; return true; } return false; } /** * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer * or the tick, whichever expires first. Note that, if the tick has been * stopped, it returns the next hrtimer. * * Called from power state control code with interrupts disabled * * Return: the next expiration time */ ktime_t tick_nohz_get_next_hrtimer(void) { return __this_cpu_read(tick_cpu_device.evtdev)->next_event; } /** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled. * * The return value of this function and/or the value returned by it through the * @delta_next pointer can be negative which must be taken into account by its * callers. * * Return: the expected length of the current sleep */ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); int cpu = smp_processor_id(); /* * The idle entry time is expected to be a sufficient approximation of * the current time at this point. */ ktime_t now = ts->idle_entrytime; ktime_t next_event; WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); *delta_next = ktime_sub(dev->next_event, now); if (!can_stop_idle_tick(cpu, ts)) return *delta_next; next_event = tick_nohz_next_event(ts, cpu); if (!next_event) return *delta_next; /* * If the next highres timer to expire is earlier than 'next_event', the * idle governor needs to know that. */ next_event = min_t(u64, next_event, hrtimer_next_event_without(&ts->sched_timer)); return ktime_sub(next_event, now); } /** * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value * for a particular CPU. * @cpu: target CPU number * * Called from the schedutil frequency scaling governor in scheduler context. * * Return: the current idle calls counter value for @cpu */ unsigned long tick_nohz_get_idle_calls_cpu(int cpu) { struct tick_sched *ts = tick_get_tick_sched(cpu); return ts->idle_calls; } static void tick_nohz_account_idle_time(struct tick_sched *ts, ktime_t now) { unsigned long ticks; ts->idle_exittime = now; if (vtime_accounting_enabled_this_cpu()) return; /* * We stopped the tick in idle. update_process_times() would miss the * time we slept, as it does only a 1 tick accounting. * Enforce that this is accounted to idle ! */ ticks = jiffies - ts->idle_jiffies; /* * We might be one off. Do not randomly account a huge number of ticks! */ if (ticks && ticks < LONG_MAX) account_idle_ticks(ticks); } void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ktime_t now = ktime_get(); tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } } static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now) { if (tick_nohz_full_cpu(smp_processor_id())) __tick_nohz_full_update_tick(ts, now); else tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); } /** * tick_nohz_idle_exit - Update the tick upon idle task exit * * When the idle task exits, update the tick depending on the * following situations: * * 1) If the CPU is not in nohz_full mode (most cases), then * restart the tick. * * 2) If the CPU is in nohz_full mode (corner case): * 2.1) If the tick can be kept stopped (no tick dependencies) * then re-evaluate the next tick and try to keep it stopped * as long as possible. * 2.2) If the tick has dependencies, restart the tick. * */ void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); WARN_ON_ONCE(ts->timer_expires_base); tick_sched_flag_clear(ts, TS_FLAG_INIDLE); idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE); tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); if (idle_active || tick_stopped) now = ktime_get(); if (idle_active) tick_nohz_stop_idle(ts, now); if (tick_stopped) tick_nohz_idle_update_tick(ts, now); local_irq_enable(); } /* * In low-resolution mode, the tick handler must be implemented directly * at the clockevent level. hrtimer can't be used instead, because its * infrastructure actually relies on the tick itself as a backend in * low-resolution mode (see hrtimer_run_queues()). */ static void tick_nohz_lowres_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); dev->next_event = KTIME_MAX; if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART)) tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } static inline void tick_nohz_activate(struct tick_sched *ts) { if (!tick_nohz_enabled) return; tick_sched_flag_set(ts, TS_FLAG_NOHZ); /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); } /** * tick_nohz_switch_to_nohz - switch to NOHZ mode */ static void tick_nohz_switch_to_nohz(void) { if (!tick_nohz_enabled) return; if (tick_switch_to_oneshot(tick_nohz_lowres_handler)) return; /* * Recycle the hrtimer in 'ts', so we can share the * highres code. */ tick_setup_sched_timer(false); } static inline void tick_nohz_irq_enter(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE)) return; now = ktime_get(); if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) tick_nohz_stop_idle(ts, now); /* * If all CPUs are idle we may need to update a stale jiffies value. * Note nohz_full is a special case: a timekeeper is guaranteed to stay * alive but it might be busy looping with interrupts disabled in some * rare case (typically stop machine). So we must make sure we have a * last resort. */ if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_update_jiffies(now); } #else static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } static inline void tick_nohz_activate(struct tick_sched *ts) { } #endif /* CONFIG_NO_HZ_COMMON */ /* * Called from irq_enter() to notify about the possible interruption of idle() */ void tick_irq_enter(void) { tick_check_oneshot_broadcast_this_cpu(); tick_nohz_irq_enter(); } static int sched_skew_tick; static int __init skew_tick(char *str) { get_option(&str, &sched_skew_tick); return 0; } early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer * @hrtimer: whether to use the hrtimer or not */ void tick_setup_sched_timer(bool hrtimer) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); /* Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) { tick_sched_flag_set(ts, TS_FLAG_HIGHRES); ts->sched_timer.function = tick_nohz_handler; } /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); /* Offset the tick to avert 'jiffies_lock' contention. */ if (sched_skew_tick) { u64 offset = TICK_NSEC >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); hrtimer_add_expires_ns(&ts->sched_timer, offset); } hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); else tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts); } /* * Shut down the tick and make sure the CPU won't try to retake the timekeeping * duty before disabling IRQs in idle for the last time. */ void tick_sched_timer_dying(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; /* This must happen before hrtimers are migrated! */ if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) hrtimer_cancel(&ts->sched_timer); idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; idle_calls = ts->idle_calls; idle_sleeps = ts->idle_sleeps; memset(ts, 0, sizeof(*ts)); ts->idle_sleeptime = idle_sleeptime; ts->iowait_sleeptime = iowait_sleeptime; ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } /* * Async notification about clocksource changes */ void tick_clock_notify(void) { int cpu; for_each_possible_cpu(cpu) set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks); } /* * Async notification about clock event changes */ void tick_oneshot_notify(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); set_bit(0, &ts->check_clocks); } /* * Check if a change happened, which makes oneshot possible. * * Called cyclically from the hrtimer softirq (driven by the timer * softirq). 'allow_nohz' signals that we can switch into low-res NOHZ * mode, because high resolution timers are disabled (either compile * or runtime). Called with interrupts disabled. */ int tick_check_oneshot_change(int allow_nohz) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) return 0; if (!allow_nohz) return 1; tick_nohz_switch_to_nohz(); return 0; } |
| 5 5 2 5 5 2 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | // SPDX-License-Identifier: GPL-2.0-only /* * ratelimit.c - Do something with rate limit. * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * * 2008-05-01 rewrite the function and use a ratelimit_state data struct as * parameter. Now every user can use their own standalone ratelimit_state. */ #include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/export.h> /* * __ratelimit - rate limiting * @rs: ratelimit_state data * @func: name of calling function * * This enforces a rate limit: not more than @rs->burst callbacks * in every @rs->interval * * RETURNS: * 0 means callbacks will be suppressed. * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). * Changing two values seperately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); int burst = READ_ONCE(rs->burst); unsigned long flags; int ret; if (!interval) return 1; /* * If we contend on this state's lock then almost * by definition we are too busy to print a message, * in addition to the one that will be printed by * the entity that is holding the lock already: */ if (!raw_spin_trylock_irqsave(&rs->lock, flags)) return 0; if (!rs->begin) rs->begin = jiffies; if (time_is_before_jiffies(rs->begin + interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { printk_deferred(KERN_WARNING "%s: %d callbacks suppressed\n", func, rs->missed); rs->missed = 0; } } rs->begin = jiffies; rs->printed = 0; } if (burst && burst > rs->printed) { rs->printed++; ret = 1; } else { rs->missed++; ret = 0; } raw_spin_unlock_irqrestore(&rs->lock, flags); return ret; } EXPORT_SYMBOL(___ratelimit); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ ifa = rtnl_net_dereference(net, ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 2 433 259 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_LOCK_H_ #define _ASM_GENERIC_BITOPS_LOCK_H_ #include <linux/atomic.h> #include <linux/compiler.h> #include <asm/barrier.h> /** * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock * @nr: Bit to set * @addr: Address to count from * * This operation is atomic and provides acquire barrier semantics if * the returned value is 0. * It can be used to implement bit locks. */ static __always_inline int arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); if (READ_ONCE(*p) & mask) return 1; old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); return !!(old & mask); } /** * arch_clear_bit_unlock - Clear a bit in memory, for unlock * @nr: the bit to set * @addr: the address to start counting from * * This operation is atomic and provides release barrier semantics. */ static __always_inline void arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); } /** * arch___clear_bit_unlock - Clear a bit in memory, for unlock * @nr: the bit to set * @addr: the address to start counting from * * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all * the bits in the word are protected by this lock some archs can use weaker * ops to safely unlock. * * See for example x86's implementation. */ static inline void arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p) { unsigned long old; p += BIT_WORD(nr); old = READ_ONCE(*p); old &= ~BIT_MASK(nr); raw_atomic_long_set_release((atomic_long_t *)p, old); } #ifndef arch_xor_unlock_is_negative_byte static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *p) { long old; old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p); return !!(old & BIT(7)); } #endif #include <asm-generic/bitops/instrumented-lock.h> #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ |
| 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { struct folio *folio; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr); if (folio && user_alloc_needs_zeroing()) clear_user_highpage(&folio->page, vaddr); return folio; } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) { } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_highmem(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } static inline void unmap_and_put_page(struct page *page, void *addr) { folio_release_kmap(page_folio(page), addr); } #endif /* _LINUX_HIGHMEM_H */ |
| 112 112 112 112 112 112 111 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analogous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the * caller is responsible for taking RCU. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; WARN_ON_ONCE(!rcu_read_lock_held()); if (likely(__ref_is_percpu(ref, &percpu_count))) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } return ret; } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { bool ret = false; rcu_read_lock(); ret = percpu_ref_tryget_live_rcu(ref); rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 529 529 529 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Procedures for maintaining information about logical memory blocks. * * Peter Bergner, IBM Corp. June 2001. * Copyright (C) 2001 Peter Bergner. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/bitops.h> #include <linux/poison.h> #include <linux/pfn.h> #include <linux/debugfs.h> #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> #include <asm/sections.h> #include <linux/io.h> #include "internal.h" #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 #ifndef INIT_MEMBLOCK_RESERVED_REGIONS # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif #ifndef INIT_MEMBLOCK_MEMORY_REGIONS #define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS #endif /** * DOC: memblock overview * * Memblock is a method of managing memory regions during the early * boot period when the usual kernel memory allocators are not up and * running. * * Memblock views the system memory as collections of contiguous * regions. There are several types of these collections: * * * ``memory`` - describes the physical memory available to the * kernel; this may differ from the actual physical memory installed * in the system, for instance when the memory is restricted with * ``mem=`` command line parameter * * ``reserved`` - describes the regions that were allocated * * ``physmem`` - describes the actual physical memory available during * boot regardless of the possible restrictions and memory hot(un)plug; * the ``physmem`` type is only available on some architectures. * * Each region is represented by struct memblock_region that * defines the region extents, its attributes and NUMA node id on NUMA * systems. Every memory type is described by the struct memblock_type * which contains an array of memory regions along with * the allocator metadata. The "memory" and "reserved" types are nicely * wrapped with struct memblock. This structure is statically * initialized at build time. The region arrays are initially sized to * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not * overlap with areas that should be reserved, for example initrd. * * The early architecture setup should tell memblock what the physical * memory layout is by using memblock_add() or memblock_add_node() * functions. The first function does not assign the region to a NUMA * node and it is appropriate for UMA systems. Yet, it is possible to * use it on NUMA systems as well and assign the region to a NUMA node * later in the setup process using memblock_set_node(). The * memblock_add_node() performs such an assignment directly. * * Once memblock is setup the memory can be allocated using one of the * API variants: * * * memblock_phys_alloc*() - these functions return the **physical** * address of the allocated memory * * memblock_alloc*() - these functions return the **virtual** address * of the allocated memory. * * Note, that both API variants use implicit assumptions about allowed * memory ranges and the fallback methods. Consult the documentation * of memblock_alloc_internal() and memblock_alloc_range_nid() * functions for more elaborate description. * * As the system boot progresses, the architecture specific mem_init() * function frees all the memory to the buddy page allocator. * * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the * memblock data structures (except "physmem") will be discarded after the * system initialization completes. */ #ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_MEMORY_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; #endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP struct memblock_type physmem = { .regions = memblock_physmem_init_regions, .max = INIT_PHYSMEM_REGIONS, .name = "physmem", }; #endif /* * keep a pointer to &memblock.memory in the text section to use it in * __next_mem_range() and its helpers. * For architectures that do not keep memblock data after init, this * pointer will be reset to NULL at memblock_discard() */ static __refdata struct memblock_type *memblock_memory = &memblock.memory; #define for_each_memblock_type(i, memblock_type, rgn) \ for (i = 0, rgn = &memblock_type->regions[0]; \ i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) #define memblock_dbg(fmt, ...) \ do { \ if (memblock_debug) \ pr_info(fmt, ##__VA_ARGS__); \ } while (0) static int memblock_debug __initdata_memblock; static bool system_has_some_mirror __initdata_memblock; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock; static int memblock_reserved_in_slab __initdata_memblock; bool __init_memblock memblock_has_mirror(void) { return system_has_some_mirror; } static enum memblock_flags __init_memblock choose_memblock_flags(void) { return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE; } /* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { return *size = min(*size, PHYS_ADDR_MAX - base); } /* * Address comparison utilities */ unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { return ((base1 < (base2 + size2)) && (base2 < (base1 + size1))); } bool __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { unsigned long i; memblock_cap_size(base, &size); for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) return true; return false; } /** * __memblock_find_range_bottom_up - find free area utility in bottom-up * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area bottom-up. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); cand = round_up(this_start, align); if (cand < this_end && this_end - cand >= size) return cand; } return 0; } /** * __memblock_find_range_top_down - find free area utility, in top-down * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Utility called from memblock_find_in_range_node(), find free area top-down. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid, enum memblock_flags flags) { phys_addr_t this_start, this_end, cand; u64 i; for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end, NULL) { this_start = clamp(this_start, start, end); this_end = clamp(this_end, start, end); if (this_end < size) continue; cand = round_down(this_end - size, align); if (cand >= this_start) return cand; } return 0; } /** * memblock_find_in_range_node - find free area in given range and node * @size: size of free area to find * @align: alignment of free area to find * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @flags: pick from blocks based on memory attributes * * Find @size free area aligned to @align in the specified range and node. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, enum memblock_flags flags) { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); if (memblock_bottom_up()) return __memblock_find_range_bottom_up(start, end, size, align, nid, flags); else return __memblock_find_range_top_down(start, end, size, align, nid, flags); } /** * memblock_find_in_range - find free area in given range * @start: start of candidate range * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or * %MEMBLOCK_ALLOC_ACCESSIBLE * @size: size of free area to find * @align: alignment of free area to find * * Find @size free area aligned to @align in the specified range. * * Return: * Found address on success, 0 on failure. */ static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { phys_addr_t ret; enum memblock_flags flags = choose_memblock_flags(); again: ret = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (!ret && (flags & MEMBLOCK_MIRROR)) { pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); flags &= ~MEMBLOCK_MIRROR; goto again; } return ret; } static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { type->total_size -= type->regions[r].size; memmove(&type->regions[r], &type->regions[r + 1], (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ if (type->cnt == 0) { WARN_ON(type->total_size != 0); type->regions[0].base = 0; type->regions[0].size = 0; type->regions[0].flags = 0; memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } #ifndef CONFIG_ARCH_KEEP_MEMBLOCK /** * memblock_discard - discard memory and reserved arrays if they were allocated */ void __init memblock_discard(void) { phys_addr_t addr, size; if (memblock.reserved.regions != memblock_reserved_init_regions) { addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); if (memblock_reserved_in_slab) kfree(memblock.reserved.regions); else memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); if (memblock_memory_in_slab) kfree(memblock.memory.regions); else memblock_free_late(addr, size); } memblock_memory = NULL; } #endif /** * memblock_double_array - double the size of the memblock regions array * @type: memblock type of the regions array being doubled * @new_area_start: starting address of memory range to avoid overlap with * @new_area_size: size of memory range to avoid overlap with * * Double the size of the @type regions array. If memblock is being used to * allocate memory for a new reserved regions array and there is a previously * allocated memory range [@new_area_start, @new_area_start + @new_area_size] * waiting to be reserved, ensure the memory used by the new array does * not overlap. * * Return: * 0 on success, -1 on failure. */ static int __init_memblock memblock_double_array(struct memblock_type *type, phys_addr_t new_area_start, phys_addr_t new_area_size) { struct memblock_region *new_array, *old_array; phys_addr_t old_alloc_size, new_alloc_size; phys_addr_t old_size, new_size, addr, new_end; int use_slab = slab_is_available(); int *in_slab; /* We don't allow resizing until we know about the reserved regions * of memory that aren't suitable for allocation */ if (!memblock_can_resize) panic("memblock: cannot resize %s array\n", type->name); /* Calculate new doubled size */ old_size = type->max * sizeof(struct memblock_region); new_size = old_size << 1; /* * We need to allocated new one align to PAGE_SIZE, * so we can free them completely later. */ old_alloc_size = PAGE_ALIGN(old_size); new_alloc_size = PAGE_ALIGN(new_size); /* Retrieve the slab flag */ if (type == &memblock.memory) in_slab = &memblock_memory_in_slab; else in_slab = &memblock_reserved_in_slab; /* Try to find some space for it */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); addr = new_array ? __pa(new_array) : 0; } else { /* only exclude range when trying to double reserved.regions */ if (type != &memblock.reserved) new_area_start = new_area_size = 0; addr = memblock_find_in_range(new_area_start + new_area_size, memblock.current_limit, new_alloc_size, PAGE_SIZE); if (!addr && new_area_size) addr = memblock_find_in_range(0, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); new_array = addr ? __va(addr) : NULL; } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", type->name, type->max, type->max * 2); return -1; } new_end = addr + new_size - 1; memblock_dbg("memblock: %s is doubled to %ld at [%pa-%pa]", type->name, type->max * 2, &addr, &new_end); /* * Found space, we now need to move the array over before we add the * reserved region since it may be our reserved array itself that is * full. */ memcpy(new_array, type->regions, old_size); memset(new_array + type->max, 0, old_size); old_array = type->regions; type->regions = new_array; type->max <<= 1; /* Free old array. We needn't free it if the array is the static one */ if (*in_slab) kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we * needn't do it */ if (!use_slab) BUG_ON(memblock_reserve(addr, new_alloc_size)); /* Update slab flag */ *in_slab = use_slab; return 0; } /** * memblock_merge_regions - merge neighboring compatible regions * @type: memblock type to scan * @start_rgn: start scanning from (@start_rgn - 1) * @end_rgn: end scanning at (@end_rgn - 1) * Scan @type and merge neighboring compatible regions in [@start_rgn - 1, @end_rgn) */ static void __init_memblock memblock_merge_regions(struct memblock_type *type, unsigned long start_rgn, unsigned long end_rgn) { int i = 0; if (start_rgn) i = start_rgn - 1; end_rgn = min(end_rgn, type->cnt - 1); while (i < end_rgn) { struct memblock_region *this = &type->regions[i]; struct memblock_region *next = &type->regions[i + 1]; if (this->base + this->size != next->base || memblock_get_region_node(this) != memblock_get_region_node(next) || this->flags != next->flags) { BUG_ON(this->base + this->size > next->base); i++; continue; } this->size += next->size; /* move forward from next + 1, index of which is i + 2 */ memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next)); type->cnt--; end_rgn--; } } /** * memblock_insert_region - insert new memblock region * @type: memblock type to insert into * @idx: index for the insertion point * @base: base address of the new region * @size: size of the new region * @nid: node id of the new region * @flags: flags of the new region * * Insert new memblock region [@base, @base + @size) into @type at @idx. * @type must already have extra room to accommodate the new region. */ static void __init_memblock memblock_insert_region(struct memblock_type *type, int idx, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { struct memblock_region *rgn = &type->regions[idx]; BUG_ON(type->cnt >= type->max); memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); rgn->base = base; rgn->size = size; rgn->flags = flags; memblock_set_region_node(rgn, nid); type->cnt++; type->total_size += size; } /** * memblock_add_range - add new memblock region * @type: memblock type to add new region into * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) into @type. The new region * is allowed to overlap with existing ones - overlaps don't affect already * existing regions. @type is guaranteed to be minimal (all neighbouring * compatible regions are merged) after the addition. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); int idx, nr_new, start_rgn = -1, end_rgn; struct memblock_region *rgn; if (!size) return 0; /* special case for empty array */ if (type->regions[0].size == 0) { WARN_ON(type->cnt != 0 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; type->regions[0].flags = flags; memblock_set_region_node(&type->regions[0], nid); type->total_size = size; type->cnt = 1; return 0; } /* * The worst case is when new range overlaps all existing regions, * then we'll need type->cnt + 1 empty regions in @type. So if * type->cnt * 2 + 1 is less than or equal to type->max, we know * that there is enough empty regions in @type, and we can insert * regions directly. */ if (type->cnt * 2 + 1 <= type->max) insert = true; repeat: /* * The following is executed twice. Once with %false @insert and * then with %true. The first counts the number of regions needed * to accommodate the new area. The second actually inserts them. */ base = obase; nr_new = 0; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; /* * @rgn overlaps. If it separates the lower part of new * area, insert that portion. */ if (rbase > base) { #ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } } /* area below @rend is dealt with, forget about it */ base = min(rend, end); } /* insert the remaining portion */ if (base < end) { nr_new++; if (insert) { if (start_rgn == -1) start_rgn = idx; end_rgn = idx + 1; memblock_insert_region(type, idx, base, end - base, nid, flags); } } if (!nr_new) return 0; /* * If this was the first round, resize array and repeat for actual * insertions; otherwise, merge and return. */ if (!insert) { while (type->cnt + nr_new > type->max) if (memblock_double_array(type, obase, size) < 0) return -ENOMEM; insert = true; goto repeat; } else { memblock_merge_regions(type, start_rgn, end_rgn); return 0; } } /** * memblock_add_node - add new memblock region within a NUMA node * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, &base, &end, nid, flags, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** * memblock_add - add new memblock region * @base: base address of the new region * @size: size of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } /** * memblock_validate_numa_coverage - check if amount of memory with * no node ID assigned is less than a threshold * @threshold_bytes: maximal memory size that can have unassigned node * ID (in bytes). * * A buggy firmware may report memory that does not belong to any node. * Check if amount of such memory is below @threshold_bytes. * * Return: true on success, false on failure. */ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) { unsigned long nr_pages = 0; unsigned long start_pfn, end_pfn, mem_size_mb; int nid, i; /* calculate lose page */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (!numa_valid_node(nid)) nr_pages += end_pfn - start_pfn; } if ((nr_pages << PAGE_SHIFT) > threshold_bytes) { mem_size_mb = memblock_phys_mem_size() >> 20; pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); return false; } return true; } /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for * @base: base of range to isolate * @size: size of range to isolate * @start_rgn: out parameter for the start of isolated region * @end_rgn: out parameter for the end of isolated region * * Walk @type and ensure that regions don't cross the boundaries defined by * [@base, @base + @size). Crossing regions are split at the boundaries, * which may create at most two more regions. The index of the first * region inside the range is returned in *@start_rgn and the index of the * first region after the range is returned in *@end_rgn. * * Return: * 0 on success, -errno on failure. */ static int __init_memblock memblock_isolate_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); int idx; struct memblock_region *rgn; *start_rgn = *end_rgn = 0; if (!size) return 0; /* we'll create at most two more regions */ while (type->cnt + 2 > type->max) if (memblock_double_array(type, base, size) < 0) return -ENOMEM; for_each_memblock_type(idx, type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; if (rbase >= end) break; if (rend <= base) continue; if (rbase < base) { /* * @rgn intersects from below. Split and continue * to process the next region - the new top half. */ rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { /* * @rgn intersects from above. Split and redo the * current region - the new bottom half. */ rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) *start_rgn = idx; *end_rgn = idx + 1; } } return 0; } static int __init_memblock memblock_remove_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = end_rgn - 1; i >= start_rgn; i--) memblock_remove_region(type, i); return 0; } int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_remove_range(&memblock.memory, base, size); } /** * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); } /** * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_phys_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); } int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0); } #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); } #endif /** * memblock_setclr_flag - set or clear flag for a memory region * @type: memblock type to set/clear flag for * @base: base address of the region * @size: size of the region * @set: set or clear the flag * @flag: the flag to update * * This function isolates region [@base, @base + @size), and sets/clears flag * * Return: 0 on success, -errno on failure. */ static int __init_memblock memblock_setclr_flag(struct memblock_type *type, phys_addr_t base, phys_addr_t size, int set, int flag) { int i, ret, start_rgn, end_rgn; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) { struct memblock_region *r = &type->regions[i]; if (set) r->flags |= flag; else r->flags &= ~flag; } memblock_merge_regions(type, start_rgn, end_rgn); return 0; } /** * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_HOTPLUG); } /** * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_HOTPLUG); } /** * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { if (!mirrored_kernelcore) return 0; system_has_some_mirror = true; return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_MIRROR); } /** * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. * @base: the base phys addr of the region * @size: the size of the region * * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the * direct mapping of the physical memory. These regions will still be * covered by the memory map. The struct page representing NOMAP memory * frames in the memory map will be PageReserved() * * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from * memblock, the caller must inform kmemleak to ignore that memory * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 1, MEMBLOCK_NOMAP); } /** * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region. * @base: the base phys addr of the region * @size: the size of the region * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.memory, base, size, 0, MEMBLOCK_NOMAP); } /** * memblock_reserved_mark_noinit - Mark a reserved memory region with flag * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized * for this region. * @base: the base phys addr of the region * @size: the size of the region * * struct pages will not be initialized for reserved memory regions marked with * %MEMBLOCK_RSRV_NOINIT. * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size) { return memblock_setclr_flag(&memblock.reserved, base, size, 1, MEMBLOCK_RSRV_NOINIT); } static bool should_skip_region(struct memblock_type *type, struct memblock_region *m, int nid, int flags) { int m_nid = memblock_get_region_node(m); /* we never skip regions when iterating memblock.reserved or physmem */ if (type != memblock_memory) return false; /* only memory regions are associated with nodes, check it */ if (numa_valid_node(nid) && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) return true; /* skip nomap memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; /* skip driver-managed memory unless we were asked for it explicitly */ if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) return true; return false; } /** * __next_mem_range - next function for for_each_free_mem_range() etc. * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Find the first area from *@idx which matches @nid, fill the out * parameters, and update *@idx for the next iteration. The lower 32bit of * *@idx contains index into type_a and the upper 32bit indexes the * areas before each region in type_b. For example, if type_b regions * look like the following, * * 0:[0-16), 1:[32-48), 2:[128-130) * * The upper 32bit indexes the following regions. * * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) * * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; for (; idx_a < type_a->cnt; idx_a++) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b < type_b->cnt + 1; idx_b++) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_start >= m_end) break; /* if the two regions intersect, we're done */ if (m_start < r_end) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; /* * The region which ends first is * advanced for the next iteration. */ if (m_end <= r_end) idx_a++; else idx_b++; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /** * __next_mem_range_rev - generic next function for for_each_*_range_rev() * * @idx: pointer to u64 loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes * @flags: pick from blocks based on memory attributes * @type_a: pointer to memblock_type from where the range is taken * @type_b: pointer to memblock_type which excludes memory from being taken * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL * @out_nid: ptr to int for nid of the range, can be %NULL * * Finds the next range from type_a which is not marked as unsuitable * in type_b. * * Reverse of __next_mem_range(). */ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; if (*idx == (u64)ULLONG_MAX) { idx_a = type_a->cnt - 1; if (type_b != NULL) idx_b = type_b->cnt; else idx_b = 0; } for (; idx_a >= 0; idx_a--) { struct memblock_region *m = &type_a->regions[idx_a]; phys_addr_t m_start = m->base; phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { if (out_start) *out_start = m_start; if (out_end) *out_end = m_end; if (out_nid) *out_nid = m_nid; idx_a--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } /* scan areas before each reservation */ for (; idx_b >= 0; idx_b--) { struct memblock_region *r; phys_addr_t r_start; phys_addr_t r_end; r = &type_b->regions[idx_b]; r_start = idx_b ? r[-1].base + r[-1].size : 0; r_end = idx_b < type_b->cnt ? r->base : PHYS_ADDR_MAX; /* * if idx_b advanced past idx_a, * break out to advance idx_a */ if (r_end <= m_start) break; /* if the two regions intersect, we're done */ if (m_end > r_start) { if (out_start) *out_start = max(m_start, r_start); if (out_end) *out_end = min(m_end, r_end); if (out_nid) *out_nid = m_nid; if (m_start >= r_start) idx_a--; else idx_b--; *idx = (u32)idx_a | (u64)idx_b << 32; return; } } } /* signal end of iteration */ *idx = ULLONG_MAX; } /* * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid) { struct memblock_type *type = &memblock.memory; struct memblock_region *r; int r_nid; while (++*idx < type->cnt) { r = &type->regions[*idx]; r_nid = memblock_get_region_node(r); if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; if (!numa_valid_node(nid) || nid == r_nid) break; } if (*idx >= type->cnt) { *idx = -1; return; } if (out_start_pfn) *out_start_pfn = PFN_UP(r->base); if (out_end_pfn) *out_end_pfn = PFN_DOWN(r->base + r->size); if (out_nid) *out_nid = r_nid; } /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for * @size: size of area to set node ID for * @type: memblock type to set node ID for * @nid: node ID to set * * Set the nid of memblock @type regions in [@base, @base + @size) to @nid. * Regions which cross the area boundaries are split as necessary. * * Return: * 0 on success, -errno on failure. */ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { #ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); if (ret) return ret; for (i = start_rgn; i < end_rgn; i++) memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type, start_rgn, end_rgn); #endif return 0; } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() * * @idx: pointer to u64 loop variable * @zone: zone in which all of the memory blocks reside * @out_spfn: ptr to ulong for start pfn of the range, can be %NULL * @out_epfn: ptr to ulong for end pfn of the range, can be %NULL * * This function is meant to be a zone/pfn specific wrapper for the * for_each_mem_range type iterators. Specifically they are used in the * deferred memory init routines and as such we were duplicating much of * this logic throughout the code. So instead of having it in multiple * locations it seemed like it would make more sense to centralize this to * one new iterator that does everything they need. */ void __init_memblock __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn) { int zone_nid = zone_to_nid(zone); phys_addr_t spa, epa; __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); while (*idx != U64_MAX) { unsigned long epfn = PFN_DOWN(epa); unsigned long spfn = PFN_UP(spa); /* * Verify the end is at least past the start of the zone and * that we have at least one PFN to initialize. */ if (zone->zone_start_pfn < epfn && spfn < epfn) { /* if we went too far just stop searching */ if (zone_end_pfn(zone) <= spfn) { *idx = U64_MAX; break; } if (out_spfn) *out_spfn = max(zone->zone_start_pfn, spfn); if (out_epfn) *out_epfn = min(zone_end_pfn(zone), epfn); return; } __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, &spa, &epa, NULL); } /* signal end of iteration */ if (out_spfn) *out_spfn = ULONG_MAX; if (out_epfn) *out_epfn = 0; } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** * memblock_alloc_range_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. * * If the specified node can not hold the requested memory and @exact_nid * is false, the allocation falls back to any node in the system. * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any * memory region. * * In addition, function using kmemleak_alloc_phys for allocated boot * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. */ phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) { void *vaddr = kzalloc_node(size, GFP_NOWAIT, nid); return vaddr ? virt_to_phys(vaddr) : 0; } if (!align) { /* Can't use WARNs this early in boot on powerpc */ dump_stack(); align = SMP_CACHE_BYTES; } again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) goto done; if (numa_valid_node(nid) && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); if (found && !memblock_reserve(found, size)) goto done; } if (flags & MEMBLOCK_MIRROR) { flags &= ~MEMBLOCK_MIRROR; pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); goto again; } return 0; done: /* * Skip kmemleak for those places like kasan_init() and * early_pgtable_alloc() due to high volume. */ if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * Memblock allocated blocks are never reported as * leaks. This is because many of these blocks are * only referred via the physical address which is * not looked up by kmemleak. */ kmemleak_alloc_phys(found, size, 0); /* * Some Virtual Machine platforms, such as Intel TDX or AMD SEV-SNP, * require memory to be accepted before it can be used by the * guest. * * Accept the memory of the allocated buffer. */ accept_memory(found, size); return found; } /** * memblock_phys_alloc_range - allocate a memory block inside specified range * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @start: the lower bound of the memory region to allocate (physical address) * @end: the upper bound of the memory region to allocate (physical address) * * Allocate @size bytes in the between @start and @end. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end) { memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, &start, &end, (void *)_RET_IP_); return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, false); } /** * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Allocates memory block from the specified NUMA node. If the node * has no available memory, attempts to allocated from any node in the * system. * * Return: physical address of the allocated memory block on success, * %0 on failure. */ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. * * The @min_addr limit is dropped if it can not be satisfied and the allocation * will fall back to memory below @min_addr. Other constraints, such * as node and mirrored memory will be handled again in * memblock_alloc_range_nid(). * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid, bool exact_nid) { phys_addr_t alloc; if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, exact_nid); if (!alloc) return NULL; return phys_to_virt(alloc); } /** * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node * without zeroing memory * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_exact_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, true); } /** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. Does not zero allocated memory, does not panic if request * cannot be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); return memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); } /** * memblock_alloc_try_nid - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * * Public function, provides additional debug information (including caller * info), if enabled. This function zeroes the allocated memory. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) { void *ptr; memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); return ptr; } /** * __memblock_alloc_or_panic - Try to allocate memory and panic on failure * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @func: caller func name * * This function attempts to allocate memory using memblock_alloc, * and in case of failure, it calls panic with the formatted message. * This function should not be used directly, please use the macro memblock_alloc_or_panic. */ void *__init __memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align, const char *func) { void *addr = memblock_alloc(size, align); if (unlikely(!addr)) panic("%s: Failed to allocate %pap bytes\n", func, &size); return addr; } /** * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * This is only useful when the memblock allocator has already been torn * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; end = base + size - 1; memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); kmemleak_free_part_phys(base, size); cursor = PFN_UP(base); end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages_inc(); } } /* * Remaining API functions */ phys_addr_t __init_memblock memblock_phys_mem_size(void) { return memblock.memory.total_size; } phys_addr_t __init_memblock memblock_reserved_size(void) { return memblock.reserved.total_size; } /** * memblock_estimated_nr_free_pages - return estimated number of free pages * from memblock point of view * * During bootup, subsystems might need a rough estimate of the number of free * pages in the whole system, before precise numbers are available from the * buddy. Especially with CONFIG_DEFERRED_STRUCT_PAGE_INIT, the numbers * obtained from the buddy might be very imprecise during bootup. * * Return: * An estimated number of free pages from memblock point of view. */ unsigned long __init memblock_estimated_nr_free_pages(void) { return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); } /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { return memblock.memory.regions[0].base; } phys_addr_t __init_memblock memblock_end_of_DRAM(void) { int idx = memblock.memory.cnt - 1; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) { phys_addr_t max_addr = PHYS_ADDR_MAX; struct memblock_region *r; /* * translate the memory @limit size into the max address within one of * the memory memblock regions, if the @limit exceeds the total size * of those regions, max_addr will keep original value PHYS_ADDR_MAX */ for_each_mem_region(r) { if (limit <= r->size) { max_addr = r->base + limit; break; } limit -= r->size; } return max_addr; } void __init memblock_enforce_memory_limit(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; /* truncate both memory and reserved regions */ memblock_remove_range(&memblock.memory, max_addr, PHYS_ADDR_MAX); memblock_remove_range(&memblock.reserved, max_addr, PHYS_ADDR_MAX); } void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) { int start_rgn, end_rgn; int i, ret; if (!size) return; if (!memblock_memory->total_size) { pr_warn("%s: No memory registered yet\n", __func__); return; } ret = memblock_isolate_range(&memblock.memory, base, size, &start_rgn, &end_rgn); if (ret) return; /* remove all the MAP regions */ for (i = memblock.memory.cnt - 1; i >= end_rgn; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); for (i = start_rgn - 1; i >= 0; i--) if (!memblock_is_nomap(&memblock.memory.regions[i])) memblock_remove_region(&memblock.memory, i); /* truncate the reserved regions */ memblock_remove_range(&memblock.reserved, 0, base); memblock_remove_range(&memblock.reserved, base + size, PHYS_ADDR_MAX); } void __init memblock_mem_limit_remove_map(phys_addr_t limit) { phys_addr_t max_addr; if (!limit) return; max_addr = __find_max_addr(limit); /* @limit exceeds the total size of the memory, do nothing */ if (max_addr == PHYS_ADDR_MAX) return; memblock_cap_memory_range(0, max_addr); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) { unsigned int left = 0, right = type->cnt; do { unsigned int mid = (right + left) / 2; if (addr < type->regions[mid].base) right = mid; else if (addr >= (type->regions[mid].base + type->regions[mid].size)) left = mid + 1; else return mid; } while (left < right); return -1; } bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } bool __init_memblock memblock_is_map_memory(phys_addr_t addr) { int i = memblock_search(&memblock.memory, addr); if (i == -1) return false; return !memblock_is_nomap(&memblock.memory.regions[i]); } int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { struct memblock_type *type = &memblock.memory; int mid = memblock_search(type, PFN_PHYS(pfn)); if (mid == -1) return NUMA_NO_NODE; *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); return memblock_get_region_node(&type->regions[mid]); } /** * memblock_is_region_memory - check if a region is a subset of memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) is a subset of a memory block. * * Return: * 0 if false, non-zero if true */ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) return false; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } /** * memblock_is_region_reserved - check if a region intersects reserved memory * @base: base of region to check * @size: size of region to check * * Check if the region [@base, @base + @size) intersects a reserved * memory block. * * Return: * True if they intersect, false if not. */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { return memblock_overlaps_region(&memblock.reserved, base, size); } void __init_memblock memblock_trim_memory(phys_addr_t align) { phys_addr_t start, end, orig_start, orig_end; struct memblock_region *r; for_each_mem_region(r) { orig_start = r->base; orig_end = r->base + r->size; start = round_up(orig_start, align); end = round_down(orig_end, align); if (start == orig_start && end == orig_end) continue; if (start < end) { r->base = start; r->size = end - start; } else { memblock_remove_region(&memblock.memory, r - memblock.memory.regions); r--; } } } void __init_memblock memblock_set_current_limit(phys_addr_t limit) { memblock.current_limit = limit; } phys_addr_t __init_memblock memblock_get_current_limit(void) { return memblock.current_limit; } static void __init_memblock memblock_dump(struct memblock_type *type) { phys_addr_t base, end, size; enum memblock_flags flags; int idx; struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", type->name, type->cnt); for_each_memblock_type(idx, type, rgn) { char nid_buf[32] = ""; base = rgn->base; size = rgn->size; end = base + size - 1; flags = rgn->flags; #ifdef CONFIG_NUMA if (numa_valid_node(memblock_get_region_node(rgn))) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n", type->name, idx, &base, &end, &size, nid_buf, flags); } } static void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); pr_info(" memory size = %pa reserved size = %pa\n", &memblock.memory.total_size, &memblock.reserved.total_size); memblock_dump(&memblock.memory); memblock_dump(&memblock.reserved); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP memblock_dump(&physmem); #endif } void __init_memblock memblock_dump_all(void) { if (memblock_debug) __memblock_dump_all(); } void __init memblock_allow_resize(void) { memblock_can_resize = 1; } static int __init early_memblock(char *p) { if (p && strstr(p, "debug")) memblock_debug = 1; return 0; } early_param("memblock", early_memblock); static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) { struct page *start_pg, *end_pg; phys_addr_t pg, pgend; /* * Convert start_pfn/end_pfn to a struct page pointer. */ start_pg = pfn_to_page(start_pfn - 1) + 1; end_pg = pfn_to_page(end_pfn - 1) + 1; /* * Convert to physical addresses, and round start upwards and end * downwards. */ pg = PAGE_ALIGN(__pa(start_pg)); pgend = PAGE_ALIGN_DOWN(__pa(end_pg)); /* * If there are free pages between these, free the section of the * memmap array. */ if (pg < pgend) memblock_phys_free(pg, pgend - pg); } /* * The mem_map array can get very big. Free the unused area of the memory map. */ static void __init free_unused_memmap(void) { unsigned long start, end, prev_end = 0; int i; if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) || IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) return; /* * This relies on each bank being in address order. * The banks are sorted previously in bootmem_init(). */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { #ifdef CONFIG_SPARSEMEM /* * Take care not to free memmap entries that don't exist * due to SPARSEMEM sections which aren't present. */ start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); #endif /* * Align down here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ start = pageblock_start_pfn(start); /* * If we had a previous bank, and there is a space * between the current bank and the previous, free it. */ if (prev_end && prev_end < start) free_memmap(prev_end, start); /* * Align up here since many operations in VM subsystem * presume that there are no holes in the memory map inside * a pageblock */ prev_end = pageblock_align(end); } #ifdef CONFIG_SPARSEMEM if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { prev_end = pageblock_align(end); free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); } #endif } static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; while (start < end) { /* * Free the pages in the largest chunks alignment allows. * * __ffs() behaviour is undefined for 0. start == 0 is * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for * the case. */ if (start) order = min_t(int, MAX_PAGE_ORDER, __ffs(start)); else order = MAX_PAGE_ORDER; while (start + (1UL << order) > end) order--; memblock_free_pages(pfn_to_page(start), start, order); start += (1UL << order); } } static unsigned long __init __free_memory_core(phys_addr_t start, phys_addr_t end) { unsigned long start_pfn = PFN_UP(start); unsigned long end_pfn = min_t(unsigned long, PFN_DOWN(end), max_low_pfn); if (start_pfn >= end_pfn) return 0; __free_pages_memory(start_pfn, end_pfn); return end_pfn - start_pfn; } static void __init memmap_init_reserved_pages(void) { struct memblock_region *region; phys_addr_t start, end; int nid; /* * set nid on all reserved pages and also treat struct * pages for the NOMAP regions as PageReserved */ for_each_mem_region(region) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (memblock_is_nomap(region)) reserve_bootmem_region(start, end, nid); memblock_set_node(start, end, &memblock.reserved, nid); } /* * initialize struct pages for reserved regions that don't have * the MEMBLOCK_RSRV_NOINIT flag set */ for_each_reserved_mem_region(region) { if (!memblock_is_reserved_noinit(region)) { nid = memblock_get_region_node(region); start = region->base; end = start + region->size; if (!numa_valid_node(nid)) nid = early_pfn_to_nid(PFN_DOWN(start)); reserve_bootmem_region(start, end, nid); } } } static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; phys_addr_t start, end; u64 i; memblock_clear_hotplug(0, -1); memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) count += __free_memory_core(start, end); return count; } static int reset_managed_pages_done __initdata; static void __init reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) atomic_long_set(&z->managed_pages, 0); } void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; if (reset_managed_pages_done) return; for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); reset_managed_pages_done = 1; } /** * memblock_free_all - release free pages to the buddy allocator */ void __init memblock_free_all(void) { unsigned long pages; free_unused_memmap(); reset_all_zones_managed_pages(); pages = free_low_memory_core_early(); totalram_pages_add(pages); } /* Keep a table to reserve named memory */ #define RESERVE_MEM_MAX_ENTRIES 8 #define RESERVE_MEM_NAME_SIZE 16 struct reserve_mem_table { char name[RESERVE_MEM_NAME_SIZE]; phys_addr_t start; phys_addr_t size; }; static struct reserve_mem_table reserved_mem_table[RESERVE_MEM_MAX_ENTRIES]; static int reserved_mem_count; /* Add wildcard region with a lookup name */ static void __init reserved_mem_add(phys_addr_t start, phys_addr_t size, const char *name) { struct reserve_mem_table *map; map = &reserved_mem_table[reserved_mem_count++]; map->start = start; map->size = size; strscpy(map->name, name); } /** * reserve_mem_find_by_name - Find reserved memory region with a given name * @name: The name that is attached to a reserved memory region * @start: If found, holds the start address * @size: If found, holds the size of the address. * * @start and @size are only updated if @name is found. * * Returns: 1 if found or 0 if not found. */ int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size) { struct reserve_mem_table *map; int i; for (i = 0; i < reserved_mem_count; i++) { map = &reserved_mem_table[i]; if (!map->size) continue; if (strcmp(name, map->name) == 0) { *start = map->start; *size = map->size; return 1; } } return 0; } EXPORT_SYMBOL_GPL(reserve_mem_find_by_name); /* * Parse reserve_mem=nn:align:name */ static int __init reserve_mem(char *p) { phys_addr_t start, size, align, tmp; char *name; char *oldp; int len; if (!p) return -EINVAL; /* Check if there's room for more reserved memory */ if (reserved_mem_count >= RESERVE_MEM_MAX_ENTRIES) return -EBUSY; oldp = p; size = memparse(p, &p); if (!size || p == oldp) return -EINVAL; if (*p != ':') return -EINVAL; align = memparse(p+1, &p); if (*p != ':') return -EINVAL; /* * memblock_phys_alloc() doesn't like a zero size align, * but it is OK for this command to have it. */ if (align < SMP_CACHE_BYTES) align = SMP_CACHE_BYTES; name = p + 1; len = strlen(name); /* name needs to have length but not too big */ if (!len || len >= RESERVE_MEM_NAME_SIZE) return -EINVAL; /* Make sure that name has text */ for (p = name; *p; p++) { if (!isspace(*p)) break; } if (!*p) return -EINVAL; /* Make sure the name is not already used */ if (reserve_mem_find_by_name(name, &start, &tmp)) return -EBUSY; start = memblock_phys_alloc(size, align); if (!start) return -ENOMEM; reserved_mem_add(start, size, name); return 1; } __setup("reserve_mem=", reserve_mem); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_ARCH_KEEP_MEMBLOCK) static const char * const flagname[] = { [ilog2(MEMBLOCK_HOTPLUG)] = "HOTPLUG", [ilog2(MEMBLOCK_MIRROR)] = "MIRROR", [ilog2(MEMBLOCK_NOMAP)] = "NOMAP", [ilog2(MEMBLOCK_DRIVER_MANAGED)] = "DRV_MNG", [ilog2(MEMBLOCK_RSRV_NOINIT)] = "RSV_NIT", }; static int memblock_debug_show(struct seq_file *m, void *private) { struct memblock_type *type = m->private; struct memblock_region *reg; int i, j, nid; unsigned int count = ARRAY_SIZE(flagname); phys_addr_t end; for (i = 0; i < type->cnt; i++) { reg = &type->regions[i]; end = reg->base + reg->size - 1; nid = memblock_get_region_node(reg); seq_printf(m, "%4d: ", i); seq_printf(m, "%pa..%pa ", ®->base, &end); if (numa_valid_node(nid)) seq_printf(m, "%4d ", nid); else seq_printf(m, "%4c ", 'x'); if (reg->flags) { for (j = 0; j < count; j++) { if (reg->flags & (1U << j)) { seq_printf(m, "%s\n", flagname[j]); break; } } if (j == count) seq_printf(m, "%s\n", "UNKNOWN"); } else { seq_printf(m, "%s\n", "NONE"); } } return 0; } DEFINE_SHOW_ATTRIBUTE(memblock_debug); static int __init memblock_init_debugfs(void) { struct dentry *root = debugfs_create_dir("memblock", NULL); debugfs_create_file("memory", 0444, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", 0444, root, &memblock.reserved, &memblock_debug_fops); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP debugfs_create_file("physmem", 0444, root, &physmem, &memblock_debug_fops); #endif return 0; } __initcall(memblock_init_debugfs); #endif /* CONFIG_DEBUG_FS */ |
| 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 | /* * Linux Security Module interfaces * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2001 James Morris <jmorris@intercode.com.au> * Copyright (C) 2001 Silicon Graphics, Inc. (Trust Technology Group) * Copyright (C) 2015 Intel Corporation. * Copyright (C) 2015 Casey Schaufler <casey@schaufler-ca.com> * Copyright (C) 2016 Mellanox Techonologies * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * Due to this file being licensed under the GPL there is controversy over * whether this permits you to write a module that #includes this file * without placing your module under the GPL. Please consult a lawyer for * advice before doing this. * */ #ifndef __LINUX_LSM_HOOKS_H #define __LINUX_LSM_HOOKS_H #include <uapi/linux/lsm.h> #include <linux/security.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/xattr.h> #include <linux/static_call.h> #include <linux/unroll.h> #include <linux/jump_label.h> #include <linux/lsm_count.h> union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" #undef LSM_HOOK void *lsm_func_addr; }; /* * @key: static call key as defined by STATIC_CALL_KEY * @trampoline: static call trampoline as defined by STATIC_CALL_TRAMP * @hl: The security_hook_list as initialized by the owning LSM. * @active: Enabled when the static call has an LSM hook associated. */ struct lsm_static_call { struct static_call_key *key; void *trampoline; struct security_hook_list *hl; /* this needs to be true or false based on what the key defaults to */ struct static_key_false *active; } __randomize_layout; /* * Table of the static calls for each LSM hook. * Once the LSMs are initialized, their callbacks will be copied to these * tables such that the calls are filled backwards (from last to first). * This way, we can jump directly to the first used static call, and execute * all of them after. This essentially makes the entry point * dynamic to adapt the number of static calls to the number of callbacks. */ struct lsm_static_calls_table { #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ struct lsm_static_call NAME[MAX_LSM_COUNT]; #include <linux/lsm_hook_defs.h> #undef LSM_HOOK } __packed __randomize_layout; /** * struct lsm_id - Identify a Linux Security Module. * @lsm: name of the LSM, must be approved by the LSM maintainers * @id: LSM ID number from uapi/linux/lsm.h * * Contains the information that identifies the LSM. */ struct lsm_id { const char *name; u64 id; }; /* * Security module hook list structure. * For use with generic list macros for common operations. * * struct security_hook_list - Contents of a cacheable, mappable object. * @scalls: The beginning of the array of static calls assigned to this hook. * @hook: The callback for the hook. * @lsm: The name of the lsm that owns this hook. */ struct security_hook_list { struct lsm_static_call *scalls; union security_list_options hook; const struct lsm_id *lsmid; } __randomize_layout; /* * Security blob size or offset data. */ struct lsm_blob_sizes { int lbs_cred; int lbs_file; int lbs_ib; int lbs_inode; int lbs_sock; int lbs_superblock; int lbs_ipc; int lbs_key; int lbs_msg_msg; int lbs_perf_event; int lbs_task; int lbs_xattr_count; /* number of xattr slots in new_xattrs array */ int lbs_tun_dev; int lbs_bdev; }; /* * LSM_RET_VOID is used as the default value in LSM_HOOK definitions for void * LSM hooks (in include/linux/lsm_hook_defs.h). */ #define LSM_RET_VOID ((void) 0) /* * Initializing a security_hook_list structure takes * up a lot of space in a source file. This macro takes * care of the common case and reduces the amount of * text involved. */ #define LSM_HOOK_INIT(NAME, HOOK) \ { \ .scalls = static_calls_table.NAME, \ .hook = { .NAME = HOOK } \ } extern void security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) enum lsm_order { LSM_ORDER_FIRST = -1, /* This is only for capabilities. */ LSM_ORDER_MUTABLE = 0, LSM_ORDER_LAST = 1, /* This is only for integrity. */ }; struct lsm_info { const char *name; /* Required. */ enum lsm_order order; /* Optional: default is LSM_ORDER_MUTABLE */ unsigned long flags; /* Optional: flags describing LSM */ int *enabled; /* Optional: controlled by CONFIG_LSM */ int (*init)(void); /* Required. */ struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */ }; #define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ __used __section(".lsm_info.init") \ __aligned(sizeof(unsigned long)) #define DEFINE_EARLY_LSM(lsm) \ static struct lsm_info __early_lsm_##lsm \ __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) /* DO NOT tamper with these variables outside of the LSM framework */ extern char *lsm_names; extern struct lsm_static_calls_table static_calls_table __ro_after_init; extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; /** * lsm_get_xattr_slot - Return the next available slot and increment the index * @xattrs: array storing LSM-provided xattrs * @xattr_count: number of already stored xattrs (updated) * * Retrieve the first available slot in the @xattrs array to fill with an xattr, * and increment @xattr_count. * * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise. */ static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs, int *xattr_count) { if (unlikely(!xattrs)) return NULL; return &xattrs[(*xattr_count)++]; } #endif /* ! __LINUX_LSM_HOOKS_H */ |
| 94 92 3 2 95 95 94 95 94 95 1 2 2 1 91 80 78 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Debug and Guest Debug support * * Copyright (C) 2015 - Linaro Ltd * Authors: Alex Bennée <alex.bennee@linaro.org> * Oliver Upton <oliver.upton@linux.dev> */ #include <linux/kvm_host.h> #include <linux/hw_breakpoint.h> #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> /** * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value * * @vcpu: the vcpu pointer * * This ensures we will trap access to: * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * - Self-hosted Trace (MDCR_EL2_TTRF/MDCR_EL2_E2TB) */ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) { preempt_disable(); /* * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK * to disable guest access to the profiling and trace buffers */ vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN, *host_data_ptr(nr_event_counters)); vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); /* Is the VM being debugged by userspace? */ if (vcpu->guest_debug) /* Route all software debug exceptions to EL2 */ vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; /* * Trap debug registers if the guest doesn't have ownership of them. */ if (!kvm_guest_owns_debug_regs(vcpu)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; /* Write MDCR_EL2 directly if we're already at EL2 */ if (has_vhe()) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); preempt_enable(); } void kvm_init_host_debug_data(void) { u64 dfr0 = read_sysreg(id_aa64dfr0_el1); if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0) *host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N, read_sysreg(pmcr_el0)); *host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0); *host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0); if (has_vhe()) return; if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P)) host_data_set_flag(HAS_SPE); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) { /* Force disable trace in protected mode in case of no TRBE */ if (is_protected_kvm_enabled()) host_data_set_flag(EL1_TRACING_CONFIGURED); if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) && !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P)) host_data_set_flag(HAS_TRBE); } } /* * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host * has taken over MDSCR_EL1. * * - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1. * * - Userspace is using the breakpoint/watchpoint registers to debug the * guest, and MDSCR_EL1.MDE is forced to 1. * * - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0, * masking all debug exceptions affected by the OS Lock. */ static void setup_external_mdscr(struct kvm_vcpu *vcpu) { /* * Use the guest's MDSCR_EL1 as a starting point, since there are * several other features controlled by MDSCR_EL1 that are not relevant * to the host. * * Clear the bits that KVM may use which also satisfies emulation of * the OS Lock as MDSCR_EL1.MDE is cleared. */ u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS | MDSCR_EL1_MDE | MDSCR_EL1_KDE); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) mdscr |= MDSCR_EL1_SS; if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE; vcpu->arch.external_mdscr_el1 = mdscr; } void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu) { u64 mdscr; /* Must be called before kvm_vcpu_load_vhe() */ KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm); /* * Determine which of the possible debug states we're in: * * - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's * breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do * software step or emulate the effects of the OS Lock being enabled. * * - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and * the breakpoint/watchpoint registers need to be loaded eagerly. * * - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint * context needs to be loaded on the CPU. */ if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) { vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED; setup_external_mdscr(vcpu); /* * Steal the guest's single-step state machine if userspace wants * single-step the guest. */ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS) vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING); else vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING); if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; else *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } } else { mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1); if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE)) vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; else vcpu->arch.debug_owner = VCPU_DEBUG_FREE; } kvm_arm_setup_mdcr_el2(vcpu); } void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu) { if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) return; /* * Save the host's software step state and restore the guest's before * potentially returning to userspace. */ if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)) vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING); else vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING); if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING)) *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; else *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; } /* * Updates ownership of the debug registers after a trapped guest access to a * breakpoint/watchpoint register. Host ownership of the debug registers is of * strictly higher priority, and it is the responsibility of the VMM to emulate * guest debug exceptions in this configuration. */ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu) { if (kvm_host_owns_debug_regs(vcpu)) return; vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED; kvm_arm_setup_mdcr_el2(vcpu); } void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val) { if (val & OSLAR_EL1_OSLK) __vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK; else __vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK; preempt_disable(); kvm_arch_vcpu_put(vcpu); kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } void kvm_enable_trbe(void) { if (has_vhe() || is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; host_data_set_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_enable_trbe); void kvm_disable_trbe(void) { if (has_vhe() || is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; host_data_clear_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_disable_trbe); void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) { if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible())) return; if (has_vhe()) { write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12); return; } *host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest; if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest) host_data_set_flag(EL1_TRACING_CONFIGURED); else host_data_clear_flag(EL1_TRACING_CONFIGURED); } EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration); |
| 236 77 77 77 32 32 32 16 16 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 - Columbia University and Linaro Ltd. * Author: Jintack Lim <jintack.lim@linaro.org> */ #include <linux/bitfield.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/sysreg.h> #include "sys_regs.h" /* Protection against the sysreg repainting madness... */ #define NV_FTR(r, f) ID_AA64##r##_EL1_##f /* * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between * memory usage and potential number of different sets of S2 PTs in * the guests. Running out of S2 MMUs only affects performance (we * will invalidate them more often). */ #define S2_MMU_PER_VCPU 2 void kvm_init_nested(struct kvm *kvm) { kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; } static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) { /* * We only initialise the IPA range on the canonical MMU, which * defines the contract between KVM and userspace on where the * "hardware" is in the IPA space. This affects the validity of MMIO * exits forwarded to userspace, for example. * * For nested S2s, we use the PARange as exposed to the guest, as it * is allowed to use it at will to expose whatever memory map it * wants to its own guests as it would be on real HW. */ return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm)); } int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_s2_mmu *tmp; int num_mmus, ret = 0; /* * Let's treat memory allocation failures as benign: If we fail to * allocate anything, return an error and keep the allocated array * alive. Userspace may try to recover by intializing the vcpu * again, and there is no reason to affect the whole VM for this. */ num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU; tmp = kvrealloc(kvm->arch.nested_mmus, size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tmp) return -ENOMEM; swap(kvm->arch.nested_mmus, tmp); /* * If we went through a realocation, adjust the MMU back-pointers in * the previously initialised kvm_pgtable structures. */ if (kvm->arch.nested_mmus != tmp) for (int i = 0; i < kvm->arch.nested_mmus_size; i++) kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i]; for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++) ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]); if (ret) { for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++) kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]); return ret; } kvm->arch.nested_mmus_size = num_mmus; return 0; } struct s2_walk_info { int (*read_desc)(phys_addr_t pa, u64 *desc, void *data); void *data; u64 baddr; unsigned int max_oa_bits; unsigned int pgshift; unsigned int sl; unsigned int t0sz; bool be; }; static u32 compute_fsc(int level, u32 fsc) { return fsc | (level & 0x3); } static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc) { u32 esr; esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC; esr |= compute_fsc(level, fsc); return esr; } static int get_ia_size(struct s2_walk_info *wi) { return 64 - wi->t0sz; } static int check_base_s2_limits(struct s2_walk_info *wi, int level, int input_size, int stride) { int start_size, ia_size; ia_size = get_ia_size(wi); /* Check translation limits */ switch (BIT(wi->pgshift)) { case SZ_64K: if (level == 0 || (level == 1 && ia_size <= 42)) return -EFAULT; break; case SZ_16K: if (level == 0 || (level == 1 && ia_size <= 40)) return -EFAULT; break; case SZ_4K: if (level < 0 || (level == 0 && ia_size <= 42)) return -EFAULT; break; } /* Check input size limits */ if (input_size > ia_size) return -EFAULT; /* Check number of entries in starting level table */ start_size = input_size - ((3 - level) * stride + wi->pgshift); if (start_size < 1 || start_size > stride + 4) return -EFAULT; return 0; } /* Check if output is within boundaries */ static int check_output_size(struct s2_walk_info *wi, phys_addr_t output) { unsigned int output_size = wi->max_oa_bits; if (output_size != 48 && (output & GENMASK_ULL(47, output_size))) return -1; return 0; } /* * This is essentially a C-version of the pseudo code from the ARM ARM * AArch64.TranslationTableWalk function. I strongly recommend looking at * that pseudocode in trying to understand this. * * Must be called with the kvm->srcu read lock held */ static int walk_nested_s2_pgd(phys_addr_t ipa, struct s2_walk_info *wi, struct kvm_s2_trans *out) { int first_block_level, level, stride, input_size, base_lower_bound; phys_addr_t base_addr; unsigned int addr_top, addr_bottom; u64 desc; /* page table entry */ int ret; phys_addr_t paddr; switch (BIT(wi->pgshift)) { default: case SZ_64K: case SZ_16K: level = 3 - wi->sl; first_block_level = 2; break; case SZ_4K: level = 2 - wi->sl; first_block_level = 1; break; } stride = wi->pgshift - 3; input_size = get_ia_size(wi); if (input_size > 48 || input_size < 25) return -EFAULT; ret = check_base_s2_limits(wi, level, input_size, stride); if (WARN_ON(ret)) return ret; base_lower_bound = 3 + input_size - ((3 - level) * stride + wi->pgshift); base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound); if (check_output_size(wi, base_addr)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); return 1; } addr_top = input_size - 1; while (1) { phys_addr_t index; addr_bottom = (3 - level) * stride + wi->pgshift; index = (ipa & GENMASK_ULL(addr_top, addr_bottom)) >> (addr_bottom - 3); paddr = base_addr | index; ret = wi->read_desc(paddr, &desc, wi->data); if (ret < 0) return ret; /* * Handle reversedescriptors if endianness differs between the * host and the guest hypervisor. */ if (wi->be) desc = be64_to_cpu((__force __be64)desc); else desc = le64_to_cpu((__force __le64)desc); /* Check for valid descriptor at this point */ if (!(desc & 1) || ((desc & 3) == 1 && level == 3)) { out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } /* We're at the final level or block translation level */ if ((desc & 3) == 1 || level == 3) break; if (check_output_size(wi, desc)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); out->desc = desc; return 1; } base_addr = desc & GENMASK_ULL(47, wi->pgshift); level += 1; addr_top = addr_bottom - 1; } if (level < first_block_level) { out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } if (check_output_size(wi, desc)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); out->desc = desc; return 1; } if (!(desc & BIT(10))) { out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS); out->desc = desc; return 1; } addr_bottom += contiguous_bit_shift(desc, wi, level); /* Calculate and return the result */ paddr = (desc & GENMASK_ULL(47, addr_bottom)) | (ipa & GENMASK_ULL(addr_bottom - 1, 0)); out->output = paddr; out->block_size = 1UL << ((3 - level) * stride + wi->pgshift); out->readable = desc & (0b01 << 6); out->writable = desc & (0b10 << 6); out->level = level; out->desc = desc; return 0; } static int read_guest_s2_desc(phys_addr_t pa, u64 *desc, void *data) { struct kvm_vcpu *vcpu = data; return kvm_read_guest(vcpu->kvm, pa, desc, sizeof(*desc)); } static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi) { wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK; switch (vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: wi->pgshift = 12; break; case VTCR_EL2_TG0_16K: wi->pgshift = 14; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ wi->pgshift = 16; break; } wi->sl = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); /* Global limit for now, should eventually be per-VM */ wi->max_oa_bits = min(get_kvm_ipa_limit(), ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr))); } int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa, struct kvm_s2_trans *result) { u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); struct s2_walk_info wi; int ret; result->esr = 0; if (!vcpu_has_nv(vcpu)) return 0; wi.read_desc = read_guest_s2_desc; wi.data = vcpu; wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); vtcr_to_walk_info(vtcr, &wi); wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE; ret = walk_nested_s2_pgd(gipa, &wi, result); if (ret) result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC); return ret; } static unsigned int ttl_to_size(u8 ttl) { int level = ttl & 3; int gran = (ttl >> 2) & 3; unsigned int max_size = 0; switch (gran) { case TLBI_TTL_TG_4K: switch (level) { case 0: break; case 1: max_size = SZ_1G; break; case 2: max_size = SZ_2M; break; case 3: max_size = SZ_4K; break; } break; case TLBI_TTL_TG_16K: switch (level) { case 0: case 1: break; case 2: max_size = SZ_32M; break; case 3: max_size = SZ_16K; break; } break; case TLBI_TTL_TG_64K: switch (level) { case 0: case 1: /* No 52bit IPA support */ break; case 2: max_size = SZ_512M; break; case 3: max_size = SZ_64K; break; } break; default: /* No size information */ break; } return max_size; } /* * Compute the equivalent of the TTL field by parsing the shadow PT. The * granule size is extracted from the cached VTCR_EL2.TG0 while the level is * retrieved from first entry carrying the level as a tag. */ static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr) { u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr; kvm_pte_t pte; u8 ttl, level; lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(mmu)->mmu_lock); switch (vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: ttl = (TLBI_TTL_TG_4K << 2); break; case VTCR_EL2_TG0_16K: ttl = (TLBI_TTL_TG_16K << 2); break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ ttl = (TLBI_TTL_TG_64K << 2); break; } tmp = addr; again: /* Iteratively compute the block sizes for a particular granule size */ switch (vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: if (sz < SZ_4K) sz = SZ_4K; else if (sz < SZ_2M) sz = SZ_2M; else if (sz < SZ_1G) sz = SZ_1G; else sz = 0; break; case VTCR_EL2_TG0_16K: if (sz < SZ_16K) sz = SZ_16K; else if (sz < SZ_32M) sz = SZ_32M; else sz = 0; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ if (sz < SZ_64K) sz = SZ_64K; else if (sz < SZ_512M) sz = SZ_512M; else sz = 0; break; } if (sz == 0) return 0; tmp &= ~(sz - 1); if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL)) goto again; if (!(pte & PTE_VALID)) goto again; level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte); if (!level) goto again; ttl |= level; /* * We now have found some level information in the shadow S2. Check * that the resulting range is actually including the original IPA. */ sz = ttl_to_size(ttl); if (addr < (tmp + sz)) return ttl; return 0; } unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); unsigned long max_size; u8 ttl; ttl = FIELD_GET(TLBI_TTL_MASK, val); if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) { /* No TTL, check the shadow S2 for a hint */ u64 addr = (val & GENMASK_ULL(35, 0)) << 12; ttl = get_guest_mapping_ttl(mmu, addr); } max_size = ttl_to_size(ttl); if (!max_size) { /* Compute the maximum extent of the invalidation */ switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: max_size = SZ_1G; break; case VTCR_EL2_TG0_16K: max_size = SZ_32M; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ /* * No, we do not support 52bit IPA in nested yet. Once * we do, this should be 4TB. */ max_size = SZ_512M; break; } } WARN_ON(!max_size); return max_size; } /* * We can have multiple *different* MMU contexts with the same VMID: * * - S2 being enabled or not, hence differing by the HCR_EL2.VM bit * * - Multiple vcpus using private S2s (huh huh...), hence differing by the * VBBTR_EL2.BADDR address * * - A combination of the above... * * We can always identify which MMU context to pick at run-time. However, * TLB invalidation involving a VMID must take action on all the TLBs using * this particular VMID. This translates into applying the same invalidation * operation to all the contexts that are using this VMID. Moar phun! */ void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid, const union tlbi_info *info, void (*tlbi_callback)(struct kvm_s2_mmu *, const union tlbi_info *)) { write_lock(&kvm->mmu_lock); for (int i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!kvm_s2_mmu_valid(mmu)) continue; if (vmid == get_vmid(mmu->tlb_vttbr)) tlbi_callback(mmu, info); } write_unlock(&kvm->mmu_lock); } struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; bool nested_stage2_enabled; u64 vttbr, vtcr, hcr; lockdep_assert_held_write(&kvm->mmu_lock); vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); hcr = vcpu_read_sys_reg(vcpu, HCR_EL2); nested_stage2_enabled = hcr & HCR_VM; /* Don't consider the CnP bit for the vttbr match */ vttbr &= ~VTTBR_CNP_BIT; /* * Two possibilities when looking up a S2 MMU context: * * - either S2 is enabled in the guest, and we need a context that is * S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR, * which makes it safe from a TLB conflict perspective (a broken * guest won't be able to generate them), * * - or S2 is disabled, and we need a context that is S2-disabled * and matches the VMID only, as all TLBs are tagged by VMID even * if S2 translation is disabled. */ for (int i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!kvm_s2_mmu_valid(mmu)) continue; if (nested_stage2_enabled && mmu->nested_stage2_enabled && vttbr == mmu->tlb_vttbr && vtcr == mmu->tlb_vtcr) return mmu; if (!nested_stage2_enabled && !mmu->nested_stage2_enabled && get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr)) return mmu; } return NULL; } static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_s2_mmu *s2_mmu; int i; lockdep_assert_held_write(&vcpu->kvm->mmu_lock); s2_mmu = lookup_s2_mmu(vcpu); if (s2_mmu) goto out; /* * Make sure we don't always search from the same point, or we * will always reuse a potentially active context, leaving * free contexts unused. */ for (i = kvm->arch.nested_mmus_next; i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next); i++) { s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size]; if (atomic_read(&s2_mmu->refcnt) == 0) break; } BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */ /* Set the scene for the next search */ kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size; /* Make sure we don't forget to do the laundry */ if (kvm_s2_mmu_valid(s2_mmu)) s2_mmu->pending_unmap = true; /* * The virtual VMID (modulo CnP) will be used as a key when matching * an existing kvm_s2_mmu. * * We cache VTCR at allocation time, once and for all. It'd be great * if the guest didn't screw that one up, as this is not very * forgiving... */ s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT; s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM; out: atomic_inc(&s2_mmu->refcnt); /* * Set the vCPU request to perform an unmap, even if the pending unmap * originates from another vCPU. This guarantees that the MMU has been * completely unmapped before any vCPU actually uses it, and allows * multiple vCPUs to lend a hand with completing the unmap. */ if (s2_mmu->pending_unmap) kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu); return s2_mmu; } void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu) { /* CnP being set denotes an invalid entry */ mmu->tlb_vttbr = VTTBR_CNP_BIT; mmu->nested_stage2_enabled = false; atomic_set(&mmu->refcnt, 0); } void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu) { /* * The vCPU kept its reference on the MMU after the last put, keep * rolling with it. */ if (vcpu->arch.hw_mmu) return; if (is_hyp_ctxt(vcpu)) { vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; } else { write_lock(&vcpu->kvm->mmu_lock); vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu); write_unlock(&vcpu->kvm->mmu_lock); } } void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu) { /* * Keep a reference on the associated stage-2 MMU if the vCPU is * scheduling out and not in WFI emulation, suggesting it is likely to * reuse the MMU sometime soon. */ if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI)) return; if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) atomic_dec(&vcpu->arch.hw_mmu->refcnt); vcpu->arch.hw_mmu = NULL; } /* * Returns non-zero if permission fault is handled by injecting it to the next * level hypervisor. */ int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans) { bool forward_fault = false; trans->esr = 0; if (!kvm_vcpu_trap_is_permission_fault(vcpu)) return 0; if (kvm_vcpu_trap_is_iabt(vcpu)) { forward_fault = !kvm_s2_trans_executable(trans); } else { bool write_fault = kvm_is_write_fault(vcpu); forward_fault = ((write_fault && !trans->writable) || (!write_fault && !trans->readable)); } if (forward_fault) trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM); return forward_fault; } int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2) { vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2); vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2); return kvm_inject_nested_sync(vcpu, esr_el2); } void kvm_nested_s2_wp(struct kvm *kvm) { int i; lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu)); } } void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block) { int i; lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block); } } void kvm_nested_s2_flush(struct kvm *kvm) { int i; lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu)); } } void kvm_arch_flush_shadow_all(struct kvm *kvm) { int i; for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!WARN_ON(atomic_read(&mmu->refcnt))) kvm_free_stage2_pgd(mmu); } kvfree(kvm->arch.nested_mmus); kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; kvm_uninit_stage2_mmu(kvm); } /* * Our emulated CPU doesn't support all the possible features. For the * sake of simplicity (and probably mental sanity), wipe out a number * of feature bits we don't intend to support for the time being. * This list should get updated as new features get added to the NV * support, and new extension to the architecture. */ static void limit_nv_id_regs(struct kvm *kvm) { u64 val, tmp; /* Support everything but TME */ val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1); val &= ~NV_FTR(ISAR0, TME); kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR0_EL1, val); /* Support everything but Spec Invalidation and LS64 */ val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1); val &= ~(NV_FTR(ISAR1, LS64) | NV_FTR(ISAR1, SPECRES)); kvm_set_vm_id_reg(kvm, SYS_ID_AA64ISAR1_EL1, val); /* No AMU, MPAM, S-EL2, or RAS */ val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1); val &= ~(GENMASK_ULL(55, 52) | NV_FTR(PFR0, AMU) | NV_FTR(PFR0, MPAM) | NV_FTR(PFR0, SEL2) | NV_FTR(PFR0, RAS) | NV_FTR(PFR0, EL3) | NV_FTR(PFR0, EL2) | NV_FTR(PFR0, EL1) | NV_FTR(PFR0, EL0)); /* 64bit only at any EL */ val |= FIELD_PREP(NV_FTR(PFR0, EL0), 0b0001); val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001); val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001); val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001); kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1, val); /* Only support BTI, SSBS, CSV2_frac */ val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1); val &= (NV_FTR(PFR1, BT) | NV_FTR(PFR1, SSBS) | NV_FTR(PFR1, CSV2_frac)); kvm_set_vm_id_reg(kvm, SYS_ID_AA64PFR1_EL1, val); /* Hide ECV, ExS, Secure Memory */ val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1); val &= ~(NV_FTR(MMFR0, ECV) | NV_FTR(MMFR0, EXS) | NV_FTR(MMFR0, TGRAN4_2) | NV_FTR(MMFR0, TGRAN16_2) | NV_FTR(MMFR0, TGRAN64_2) | NV_FTR(MMFR0, SNSMEM)); /* Disallow unsupported S2 page sizes */ switch (PAGE_SIZE) { case SZ_64K: val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0001); fallthrough; case SZ_16K: val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0001); fallthrough; case SZ_4K: /* Support everything */ break; } /* * Since we can't support a guest S2 page size smaller than * the host's own page size (due to KVM only populating its * own S2 using the kernel's page size), advertise the * limitation using FEAT_GTG. */ switch (PAGE_SIZE) { case SZ_4K: val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN4_2), 0b0010); fallthrough; case SZ_16K: val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN16_2), 0b0010); fallthrough; case SZ_64K: val |= FIELD_PREP(NV_FTR(MMFR0, TGRAN64_2), 0b0010); break; } /* Cap PARange to 48bits */ tmp = FIELD_GET(NV_FTR(MMFR0, PARANGE), val); if (tmp > 0b0101) { val &= ~NV_FTR(MMFR0, PARANGE); val |= FIELD_PREP(NV_FTR(MMFR0, PARANGE), 0b0101); } kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR0_EL1, val); val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1); val &= (NV_FTR(MMFR1, HCX) | NV_FTR(MMFR1, PAN) | NV_FTR(MMFR1, LO) | NV_FTR(MMFR1, HPDS) | NV_FTR(MMFR1, VH) | NV_FTR(MMFR1, VMIDBits)); kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR1_EL1, val); val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1); val &= ~(NV_FTR(MMFR2, BBM) | NV_FTR(MMFR2, TTL) | GENMASK_ULL(47, 44) | NV_FTR(MMFR2, ST) | NV_FTR(MMFR2, CCIDX) | NV_FTR(MMFR2, VARange)); /* Force TTL support */ val |= FIELD_PREP(NV_FTR(MMFR2, TTL), 0b0001); kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR2_EL1, val); val = 0; if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1)) val |= FIELD_PREP(NV_FTR(MMFR4, E2H0), ID_AA64MMFR4_EL1_E2H0_NI_NV1); kvm_set_vm_id_reg(kvm, SYS_ID_AA64MMFR4_EL1, val); /* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */ val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1); val &= (NV_FTR(DFR0, PMUVer) | NV_FTR(DFR0, WRPs) | NV_FTR(DFR0, BRPs) | NV_FTR(DFR0, DebugVer) | NV_FTR(DFR0, HPMN0)); /* Cap Debug to ARMv8.1 */ tmp = FIELD_GET(NV_FTR(DFR0, DebugVer), val); if (tmp > 0b0111) { val &= ~NV_FTR(DFR0, DebugVer); val |= FIELD_PREP(NV_FTR(DFR0, DebugVer), 0b0111); } kvm_set_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1, val); } u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr, u64 v) { struct kvm_sysreg_masks *masks; masks = vcpu->kvm->arch.sysreg_masks; if (masks) { sr -= __SANITISED_REG_START__; v &= ~masks->mask[sr].res0; v |= masks->mask[sr].res1; } return v; } static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1) { int i = sr - __SANITISED_REG_START__; BUILD_BUG_ON(!__builtin_constant_p(sr)); BUILD_BUG_ON(sr < __SANITISED_REG_START__); BUILD_BUG_ON(sr >= NR_SYS_REGS); kvm->arch.sysreg_masks->mask[i].res0 = res0; kvm->arch.sysreg_masks->mask[i].res1 = res1; } int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; u64 res0, res1; lockdep_assert_held(&kvm->arch.config_lock); if (kvm->arch.sysreg_masks) goto out; kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)), GFP_KERNEL_ACCOUNT); if (!kvm->arch.sysreg_masks) return -ENOMEM; limit_nv_id_regs(kvm); /* VTTBR_EL2 */ res0 = res1 = 0; if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16)) res0 |= GENMASK(63, 56); if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, CnP, IMP)) res0 |= VTTBR_CNP_BIT; set_sysreg_masks(kvm, VTTBR_EL2, res0, res1); /* VTCR_EL2 */ res0 = GENMASK(63, 32) | GENMASK(30, 20); res1 = BIT(31); set_sysreg_masks(kvm, VTCR_EL2, res0, res1); /* VMPIDR_EL2 */ res0 = GENMASK(63, 40) | GENMASK(30, 24); res1 = BIT(31); set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1); /* HCR_EL2 */ res0 = BIT(48); res1 = HCR_RW; if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, TWED, IMP)) res0 |= GENMASK(63, 59); if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, MTE2)) res0 |= (HCR_TID5 | HCR_DCT | HCR_ATA); if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, TTLBxS)) res0 |= (HCR_TTLBIS | HCR_TTLBOS); if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) && !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2)) res0 |= HCR_ENSCXT; if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, IMP)) res0 |= (HCR_TOCU | HCR_TICAB | HCR_TID4); if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1)) res0 |= HCR_AMVOFFEN; if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1)) res0 |= HCR_FIEN; if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, FWB, IMP)) res0 |= HCR_FWB; if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2)) res0 |= HCR_NV2; if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, IMP)) res0 |= (HCR_AT | HCR_NV1 | HCR_NV); if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC))) res0 |= (HCR_API | HCR_APK); if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP)) res0 |= BIT(39); if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) res0 |= (HCR_TEA | HCR_TERR); if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP)) res0 |= HCR_TLOR; if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, IMP)) res1 |= HCR_E2H; set_sysreg_masks(kvm, HCR_EL2, res0, res1); /* HCRX_EL2 */ res0 = HCRX_EL2_RES0; res1 = HCRX_EL2_RES1; if (!kvm_has_feat(kvm, ID_AA64ISAR3_EL1, PACM, TRIVIAL_IMP)) res0 |= HCRX_EL2_PACMEn; if (!kvm_has_feat(kvm, ID_AA64PFR2_EL1, FPMR, IMP)) res0 |= HCRX_EL2_EnFPM; if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP)) res0 |= HCRX_EL2_GCSEn; if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, SYSREG_128, IMP)) res0 |= HCRX_EL2_EnIDCP128; if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, DEV_ASYNC)) res0 |= (HCRX_EL2_EnSDERR | HCRX_EL2_EnSNERR); if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, DF2, IMP)) res0 |= HCRX_EL2_TMEA; if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP)) res0 |= HCRX_EL2_D128En; if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP)) res0 |= HCRX_EL2_PTTWI; if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SCTLRX, IMP)) res0 |= HCRX_EL2_SCTLR2En; if (!kvm_has_tcr2(kvm)) res0 |= HCRX_EL2_TCR2En; if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP)) res0 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2); if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, CMOW, IMP)) res0 |= HCRX_EL2_CMOW; if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, NMI, IMP)) res0 |= (HCRX_EL2_VFNMI | HCRX_EL2_VINMI | HCRX_EL2_TALLINT); if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP) || !(read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS)) res0 |= HCRX_EL2_SMPME; if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP)) res0 |= (HCRX_EL2_FGTnXS | HCRX_EL2_FnXS); if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V)) res0 |= HCRX_EL2_EnASR; if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64)) res0 |= HCRX_EL2_EnALS; if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA)) res0 |= HCRX_EL2_EnAS0; set_sysreg_masks(kvm, HCRX_EL2, res0, res1); /* HFG[RW]TR_EL2 */ res0 = res1 = 0; if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC))) res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey | HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey | HFGxTR_EL2_APIBKey); if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP)) res0 |= (HFGxTR_EL2_LORC_EL1 | HFGxTR_EL2_LOREA_EL1 | HFGxTR_EL2_LORID_EL1 | HFGxTR_EL2_LORN_EL1 | HFGxTR_EL2_LORSA_EL1); if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) && !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2)) res0 |= (HFGxTR_EL2_SCXTNUM_EL1 | HFGxTR_EL2_SCXTNUM_EL0); if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP)) res0 |= HFGxTR_EL2_ICC_IGRPENn_EL1; if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) res0 |= (HFGxTR_EL2_ERRIDR_EL1 | HFGxTR_EL2_ERRSELR_EL1 | HFGxTR_EL2_ERXFR_EL1 | HFGxTR_EL2_ERXCTLR_EL1 | HFGxTR_EL2_ERXSTATUS_EL1 | HFGxTR_EL2_ERXMISCn_EL1 | HFGxTR_EL2_ERXPFGF_EL1 | HFGxTR_EL2_ERXPFGCTL_EL1 | HFGxTR_EL2_ERXPFGCDN_EL1 | HFGxTR_EL2_ERXADDR_EL1); if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA)) res0 |= HFGxTR_EL2_nACCDATA_EL1; if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP)) res0 |= (HFGxTR_EL2_nGCS_EL0 | HFGxTR_EL2_nGCS_EL1); if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP)) res0 |= (HFGxTR_EL2_nSMPRI_EL1 | HFGxTR_EL2_nTPIDR2_EL0); if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP)) res0 |= HFGxTR_EL2_nRCWMASK_EL1; if (!kvm_has_s1pie(kvm)) res0 |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1); if (!kvm_has_s1poe(kvm)) res0 |= (HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nPOR_EL1); if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S2POE, IMP)) res0 |= HFGxTR_EL2_nS2POR_EL1; if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP)) res0 |= (HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nAMAIR2_EL1); set_sysreg_masks(kvm, HFGRTR_EL2, res0 | __HFGRTR_EL2_RES0, res1); set_sysreg_masks(kvm, HFGWTR_EL2, res0 | __HFGWTR_EL2_RES0, res1); /* HDFG[RW]TR_EL2 */ res0 = res1 = 0; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP)) res0 |= HDFGRTR_EL2_OSDLR_EL1; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) res0 |= (HDFGRTR_EL2_PMEVCNTRn_EL0 | HDFGRTR_EL2_PMEVTYPERn_EL0 | HDFGRTR_EL2_PMCCFILTR_EL0 | HDFGRTR_EL2_PMCCNTR_EL0 | HDFGRTR_EL2_PMCNTEN | HDFGRTR_EL2_PMINTEN | HDFGRTR_EL2_PMOVS | HDFGRTR_EL2_PMSELR_EL0 | HDFGRTR_EL2_PMMIR_EL1 | HDFGRTR_EL2_PMUSERENR_EL0 | HDFGRTR_EL2_PMCEIDn_EL0); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) res0 |= (HDFGRTR_EL2_PMBLIMITR_EL1 | HDFGRTR_EL2_PMBPTR_EL1 | HDFGRTR_EL2_PMBSR_EL1 | HDFGRTR_EL2_PMSCR_EL1 | HDFGRTR_EL2_PMSEVFR_EL1 | HDFGRTR_EL2_PMSFCR_EL1 | HDFGRTR_EL2_PMSICR_EL1 | HDFGRTR_EL2_PMSIDR_EL1 | HDFGRTR_EL2_PMSIRR_EL1 | HDFGRTR_EL2_PMSLATFR_EL1 | HDFGRTR_EL2_PMBIDR_EL1); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP)) res0 |= (HDFGRTR_EL2_TRC | HDFGRTR_EL2_TRCAUTHSTATUS | HDFGRTR_EL2_TRCAUXCTLR | HDFGRTR_EL2_TRCCLAIM | HDFGRTR_EL2_TRCCNTVRn | HDFGRTR_EL2_TRCID | HDFGRTR_EL2_TRCIMSPECn | HDFGRTR_EL2_TRCOSLSR | HDFGRTR_EL2_TRCPRGCTLR | HDFGRTR_EL2_TRCSEQSTR | HDFGRTR_EL2_TRCSSCSRn | HDFGRTR_EL2_TRCSTATR | HDFGRTR_EL2_TRCVICTLR); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP)) res0 |= (HDFGRTR_EL2_TRBBASER_EL1 | HDFGRTR_EL2_TRBIDR_EL1 | HDFGRTR_EL2_TRBLIMITR_EL1 | HDFGRTR_EL2_TRBMAR_EL1 | HDFGRTR_EL2_TRBPTR_EL1 | HDFGRTR_EL2_TRBSR_EL1 | HDFGRTR_EL2_TRBTRG_EL1); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) res0 |= (HDFGRTR_EL2_nBRBIDR | HDFGRTR_EL2_nBRBCTL | HDFGRTR_EL2_nBRBDATA); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2)) res0 |= HDFGRTR_EL2_nPMSNEVFR_EL1; set_sysreg_masks(kvm, HDFGRTR_EL2, res0 | HDFGRTR_EL2_RES0, res1); /* Reuse the bits from the read-side and add the write-specific stuff */ if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) res0 |= (HDFGWTR_EL2_PMCR_EL0 | HDFGWTR_EL2_PMSWINC_EL0); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP)) res0 |= HDFGWTR_EL2_TRCOSLAR; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP)) res0 |= HDFGWTR_EL2_TRFCR_EL1; set_sysreg_masks(kvm, HFGWTR_EL2, res0 | HDFGWTR_EL2_RES0, res1); /* HFGITR_EL2 */ res0 = HFGITR_EL2_RES0; res1 = HFGITR_EL2_RES1; if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, DPB, DPB2)) res0 |= HFGITR_EL2_DCCVADP; if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2)) res0 |= (HFGITR_EL2_ATS1E1RP | HFGITR_EL2_ATS1E1WP); if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS)) res0 |= (HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS | HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS | HFGITR_EL2_TLBIVAALE1OS | HFGITR_EL2_TLBIVALE1OS | HFGITR_EL2_TLBIVAAE1OS | HFGITR_EL2_TLBIASIDE1OS | HFGITR_EL2_TLBIVAE1OS | HFGITR_EL2_TLBIVMALLE1OS); if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE)) res0 |= (HFGITR_EL2_TLBIRVAALE1 | HFGITR_EL2_TLBIRVALE1 | HFGITR_EL2_TLBIRVAAE1 | HFGITR_EL2_TLBIRVAE1 | HFGITR_EL2_TLBIRVAALE1IS | HFGITR_EL2_TLBIRVALE1IS | HFGITR_EL2_TLBIRVAAE1IS | HFGITR_EL2_TLBIRVAE1IS | HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS | HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS); if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, IMP)) res0 |= (HFGITR_EL2_CFPRCTX | HFGITR_EL2_DVPRCTX | HFGITR_EL2_CPPRCTX); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) res0 |= (HFGITR_EL2_nBRBINJ | HFGITR_EL2_nBRBIALL); if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP)) res0 |= (HFGITR_EL2_nGCSPUSHM_EL1 | HFGITR_EL2_nGCSSTR_EL1 | HFGITR_EL2_nGCSEPP); if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX)) res0 |= HFGITR_EL2_COSPRCTX; if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP)) res0 |= HFGITR_EL2_ATS1E1A; set_sysreg_masks(kvm, HFGITR_EL2, res0, res1); /* HAFGRTR_EL2 - not a lot to see here */ res0 = HAFGRTR_EL2_RES0; res1 = HAFGRTR_EL2_RES1; if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1)) res0 |= ~(res0 | res1); set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1); /* TCR2_EL2 */ res0 = TCR2_EL2_RES0; res1 = TCR2_EL2_RES1; if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP)) res0 |= (TCR2_EL2_DisCH0 | TCR2_EL2_DisCH1 | TCR2_EL2_D128); if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, MEC, IMP)) res0 |= TCR2_EL2_AMEC1 | TCR2_EL2_AMEC0; if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, HAFDBS, HAFT)) res0 |= TCR2_EL2_HAFT; if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP)) res0 |= TCR2_EL2_PTTWI | TCR2_EL2_PnCH; if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP)) res0 |= TCR2_EL2_AIE; if (!kvm_has_s1poe(kvm)) res0 |= TCR2_EL2_POE | TCR2_EL2_E0POE; if (!kvm_has_s1pie(kvm)) res0 |= TCR2_EL2_PIE; if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP)) res0 |= (TCR2_EL2_E0POE | TCR2_EL2_D128 | TCR2_EL2_AMEC1 | TCR2_EL2_DisCH0 | TCR2_EL2_DisCH1); set_sysreg_masks(kvm, TCR2_EL2, res0, res1); /* SCTLR_EL1 */ res0 = SCTLR_EL1_RES0; res1 = SCTLR_EL1_RES1; if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN3)) res0 |= SCTLR_EL1_EPAN; set_sysreg_masks(kvm, SCTLR_EL1, res0, res1); /* MDCR_EL2 */ res0 = MDCR_EL2_RES0; res1 = MDCR_EL2_RES1; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) res0 |= (MDCR_EL2_HPMN | MDCR_EL2_TPMCR | MDCR_EL2_TPM | MDCR_EL2_HPME); if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) res0 |= MDCR_EL2_E2PB | MDCR_EL2_TPMS; if (!kvm_has_feat(kvm, ID_AA64DFR1_EL1, SPMU, IMP)) res0 |= MDCR_EL2_EnSPM; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P1)) res0 |= MDCR_EL2_HPMD; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP)) res0 |= MDCR_EL2_TTRF; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) res0 |= MDCR_EL2_HCCD | MDCR_EL2_HLP; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP)) res0 |= MDCR_EL2_E2TB; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, FGT, IMP)) res0 |= MDCR_EL2_TDCC; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, MTPMU, IMP) || kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL3, IMP)) res0 |= MDCR_EL2_MTPME; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, V3P7)) res0 |= MDCR_EL2_HPMFZO; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSS, IMP)) res0 |= MDCR_EL2_PMSSE; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2)) res0 |= MDCR_EL2_HPMFZS; if (!kvm_has_feat(kvm, ID_AA64DFR1_EL1, EBEP, IMP)) res0 |= MDCR_EL2_PMEE; if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, V8P9)) res0 |= MDCR_EL2_EBWE; if (!kvm_has_feat(kvm, ID_AA64DFR2_EL1, STEP, IMP)) res0 |= MDCR_EL2_EnSTEPOP; set_sysreg_masks(kvm, MDCR_EL2, res0, res1); /* CNTHCTL_EL2 */ res0 = GENMASK(63, 20); res1 = 0; if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RME, IMP)) res0 |= CNTHCTL_CNTPMASK | CNTHCTL_CNTVMASK; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, CNTPOFF)) { res0 |= CNTHCTL_ECV; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, IMP)) res0 |= (CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT | CNTHCTL_EL1NVPCT | CNTHCTL_EL1NVVCT); } if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP)) res0 |= GENMASK(11, 8); set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1); out: for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++) (void)__vcpu_sys_reg(vcpu, sr); return 0; } void check_nested_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) { struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu; write_lock(&vcpu->kvm->mmu_lock); if (mmu->pending_unmap) { kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true); mmu->pending_unmap = false; } write_unlock(&vcpu->kvm->mmu_lock); } } |
| 21 20 21 21 20 21 20 21 20 21 21 21 21 21 21 21 21 21 21 4 4 4 21 21 21 21 21 21 21 15 15 14 15 21 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* audit.c -- Auditing support * Gateway between the kernel (e.g., selinux) and the user-space audit daemon. * System-call specific features have moved to auditsc.c * * Copyright 2003-2007 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> * * Goals: 1) Integrate fully with Security Modules. * 2) Minimal run-time overhead: * a) Minimal when syscall auditing is disabled (audit_enable=0). * b) Small when syscall auditing is enabled and no audit record * is generated (defer as much work as possible to record * generation time): * i) context is allocated, * ii) names from getname are stored without a copy, and * iii) inode information stored from path_lookup. * 3) Ability to disable syscall auditing at boot time (audit=0). * 4) Usable by other parts of the kernel (if audit_log* is called, * then a syscall record will be generated automatically for the * current syscall). * 5) Netlink interface to user-space. * 6) Support low-overhead kernel-based filtering to minimize the * information that must be passed to user-space. * * Audit userspace, documentation, tests, and bug/issue trackers: * https://github.com/linux-audit */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/file.h> #include <linux/init.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/pid.h> #include <linux/audit.h> #include <net/sock.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/security.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <net/netns/generic.h> #include "audit.h" /* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. * (Initialization happens after skb_init is called.) */ #define AUDIT_DISABLED -1 #define AUDIT_UNINITIALIZED 0 #define AUDIT_INITIALIZED 1 static int audit_initialized = AUDIT_UNINITIALIZED; u32 audit_enabled = AUDIT_OFF; bool audit_ever_enabled = !!AUDIT_OFF; EXPORT_SYMBOL_GPL(audit_enabled); /* Default state when kernel boots without any parameters. */ static u32 audit_default = AUDIT_OFF; /* If auditing cannot proceed, audit_failure selects what happens. */ static u32 audit_failure = AUDIT_FAIL_PRINTK; /* private audit network namespace index */ static unsigned int audit_net_id; /** * struct audit_net - audit private network namespace data * @sk: communication socket */ struct audit_net { struct sock *sk; }; /** * struct auditd_connection - kernel/auditd connection state * @pid: auditd PID * @portid: netlink portid * @net: the associated network namespace * @rcu: RCU head * * Description: * This struct is RCU protected; you must either hold the RCU lock for reading * or the associated spinlock for writing. */ struct auditd_connection { struct pid *pid; u32 portid; struct net *net; struct rcu_head rcu; }; static struct auditd_connection __rcu *auditd_conn; static DEFINE_SPINLOCK(auditd_conn_lock); /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in * audit records being dropped. */ static u32 audit_rate_limit; /* Number of outstanding audit_buffers allowed. * When set to zero, this means unlimited. */ static u32 audit_backlog_limit = 64; #define AUDIT_BACKLOG_WAIT_TIME (60 * HZ) static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; /* The identity of the user shutting down the audit system. */ static kuid_t audit_sig_uid = INVALID_UID; static pid_t audit_sig_pid = -1; static struct lsm_prop audit_sig_lsm; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] 1) out of memory in audit_log_start [kmalloc of struct audit_buffer] 2) out of memory in audit_log_move [alloc_skb] 3) suppressed due to audit_rate_limit 4) suppressed due to audit_backlog_limit */ static atomic_t audit_lost = ATOMIC_INIT(0); /* Monotonically increasing sum of time the kernel has spent * waiting while the backlog limit is exceeded. */ static atomic_t audit_backlog_wait_time_actual = ATOMIC_INIT(0); /* Hash for inode-based rules */ struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; static struct kmem_cache *audit_buffer_cache; /* queue msgs to send via kauditd_task */ static struct sk_buff_head audit_queue; /* queue msgs due to temporary unicast send problems */ static struct sk_buff_head audit_retry_queue; /* queue msgs waiting for new auditd connection */ static struct sk_buff_head audit_hold_queue; /* queue servicing thread */ static struct task_struct *kauditd_task; static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); /* waitqueue for callers who are blocked on the audit backlog */ static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION, .mask = -1, .features = 0, .lock = 0,}; static char *audit_feature_names[2] = { "only_unset_loginuid", "loginuid_immutable", }; /** * struct audit_ctl_mutex - serialize requests from userspace * @lock: the mutex used for locking * @owner: the task which owns the lock * * Description: * This is the lock struct used to ensure we only process userspace requests * in an orderly fashion. We can't simply use a mutex/lock here because we * need to track lock ownership so we don't end up blocking the lock owner in * audit_log_start() or similar. */ static struct audit_ctl_mutex { struct mutex lock; void *owner; } audit_cmd_mutex; /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting * audit records. Since printk uses a 1024 byte buffer, this buffer * should be at least that large. */ #define AUDIT_BUFSIZ 1024 /* The audit_buffer is used when formatting an audit record. The caller * locks briefly to get the record off the freelist or to allocate the * buffer, and locks briefly to send the buffer to the netlink layer or * to place it on a transmit queue. Multiple audit_buffers can be in * use simultaneously. */ struct audit_buffer { struct sk_buff *skb; /* formatted skb ready to send */ struct audit_context *ctx; /* NULL or associated context */ gfp_t gfp_mask; }; struct audit_reply { __u32 portid; struct net *net; struct sk_buff *skb; }; /** * auditd_test_task - Check to see if a given task is an audit daemon * @task: the task to check * * Description: * Return 1 if the task is a registered audit daemon, 0 otherwise. */ int auditd_test_task(struct task_struct *task) { int rc; struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); rc = (ac && ac->pid == task_tgid(task) ? 1 : 0); rcu_read_unlock(); return rc; } /** * audit_ctl_lock - Take the audit control lock */ void audit_ctl_lock(void) { mutex_lock(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = current; } /** * audit_ctl_unlock - Drop the audit control lock */ void audit_ctl_unlock(void) { audit_cmd_mutex.owner = NULL; mutex_unlock(&audit_cmd_mutex.lock); } /** * audit_ctl_owner_current - Test to see if the current task owns the lock * * Description: * Return true if the current task owns the audit control lock, false if it * doesn't own the lock. */ static bool audit_ctl_owner_current(void) { return (current == audit_cmd_mutex.owner); } /** * auditd_pid_vnr - Return the auditd PID relative to the namespace * * Description: * Returns the PID in relation to the namespace, 0 on failure. */ static pid_t auditd_pid_vnr(void) { pid_t pid; const struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac || !ac->pid) pid = 0; else pid = pid_vnr(ac->pid); rcu_read_unlock(); return pid; } /** * audit_get_sk - Return the audit socket for the given network namespace * @net: the destination network namespace * * Description: * Returns the sock pointer if valid, NULL otherwise. The caller must ensure * that a reference is held for the network namespace while the sock is in use. */ static struct sock *audit_get_sk(const struct net *net) { struct audit_net *aunet; if (!net) return NULL; aunet = net_generic(net, audit_net_id); return aunet->sk; } void audit_panic(const char *message) { switch (audit_failure) { case AUDIT_FAIL_SILENT: break; case AUDIT_FAIL_PRINTK: if (printk_ratelimit()) pr_err("%s\n", message); break; case AUDIT_FAIL_PANIC: panic("audit: %s\n", message); break; } } static inline int audit_rate_check(void) { static unsigned long last_check = 0; static int messages = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int retval = 0; if (!audit_rate_limit) return 1; spin_lock_irqsave(&lock, flags); if (++messages < audit_rate_limit) { retval = 1; } else { now = jiffies; if (time_after(now, last_check + HZ)) { last_check = now; messages = 0; retval = 1; } } spin_unlock_irqrestore(&lock, flags); return retval; } /** * audit_log_lost - conditionally log lost audit message event * @message: the message stating reason for lost audit message * * Emit at least 1 message per second, even if audit_rate_check is * throttling. * Always increment the lost messages counter. */ void audit_log_lost(const char *message) { static unsigned long last_msg = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int print; atomic_inc(&audit_lost); print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit); if (!print) { spin_lock_irqsave(&lock, flags); now = jiffies; if (time_after(now, last_msg + HZ)) { print = 1; last_msg = now; } spin_unlock_irqrestore(&lock, flags); } if (print) { if (printk_ratelimit()) pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n", atomic_read(&audit_lost), audit_rate_limit, audit_backlog_limit); audit_panic(message); } } static int audit_log_config_change(char *function_name, u32 new, u32 old, int allow_changes) { struct audit_buffer *ab; int rc = 0; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (unlikely(!ab)) return rc; audit_log_format(ab, "op=set %s=%u old=%u ", function_name, new, old); audit_log_session_info(ab); rc = audit_log_task_context(ab); if (rc) allow_changes = 0; /* Something weird, deny request */ audit_log_format(ab, " res=%d", allow_changes); audit_log_end(ab); return rc; } static int audit_do_config_change(char *function_name, u32 *to_change, u32 new) { int allow_changes, rc = 0; u32 old = *to_change; /* check if we are locked */ if (audit_enabled == AUDIT_LOCKED) allow_changes = 0; else allow_changes = 1; if (audit_enabled != AUDIT_OFF) { rc = audit_log_config_change(function_name, new, old, allow_changes); if (rc) allow_changes = 0; } /* If we are allowed, make the change */ if (allow_changes == 1) *to_change = new; /* Not allowed, update reason */ else if (rc == 0) rc = -EPERM; return rc; } static int audit_set_rate_limit(u32 limit) { return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit); } static int audit_set_backlog_limit(u32 limit) { return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit); } static int audit_set_backlog_wait_time(u32 timeout) { return audit_do_config_change("audit_backlog_wait_time", &audit_backlog_wait_time, timeout); } static int audit_set_enabled(u32 state) { int rc; if (state > AUDIT_LOCKED) return -EINVAL; rc = audit_do_config_change("audit_enabled", &audit_enabled, state); if (!rc) audit_ever_enabled |= !!state; return rc; } static int audit_set_failure(u32 state) { if (state != AUDIT_FAIL_SILENT && state != AUDIT_FAIL_PRINTK && state != AUDIT_FAIL_PANIC) return -EINVAL; return audit_do_config_change("audit_failure", &audit_failure, state); } /** * auditd_conn_free - RCU helper to release an auditd connection struct * @rcu: RCU head * * Description: * Drop any references inside the auditd connection tracking struct and free * the memory. */ static void auditd_conn_free(struct rcu_head *rcu) { struct auditd_connection *ac; ac = container_of(rcu, struct auditd_connection, rcu); put_pid(ac->pid); put_net(ac->net); kfree(ac); } /** * auditd_set - Set/Reset the auditd connection state * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer * @skb: the netlink command from the audit daemon * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ static int auditd_set(struct pid *pid, u32 portid, struct net *net, struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; struct nlmsghdr *nlh; if (!pid || !net) return -EINVAL; ac_new = kzalloc(sizeof(*ac_new), GFP_KERNEL); if (!ac_new) return -ENOMEM; ac_new->pid = get_pid(pid); ac_new->portid = portid; ac_new->net = get_net(net); /* send the ack now to avoid a race with the queue backlog */ if (*ack) { nlh = nlmsg_hdr(skb); netlink_ack(skb, nlh, 0, NULL); *ack = false; } spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); rcu_assign_pointer(auditd_conn, ac_new); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); return 0; } /** * kauditd_printk_skb - Print the audit record to the ring buffer * @skb: audit record * * Whatever the reason, this packet may not make it to the auditd connection * so write it via printk so the information isn't completely lost. */ static void kauditd_printk_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); char *data = nlmsg_data(nlh); if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit()) pr_notice("type=%d %s\n", nlh->nlmsg_type, data); } /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { /* put the record back in the queue */ skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this * function is called we haven't given up yet on sending the record, but things * are not looking good. The first thing we want to do is try to write the * record via printk and then see if we want to try and hold on to the record * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ if (!audit_default) goto drop; /* the hold queue is only for when the daemon goes away completely, * not -EAGAIN failures; if we are in a -EAGAIN state requeue the * record on the retry queue unless it's full, in which case drop it */ if (error == -EAGAIN) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } audit_log_lost("kauditd retry queue overflow"); goto drop; } /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); return; } /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } /* we have to drop the record, send it via printk as a last effort */ kauditd_printk_skb(skb); audit_log_lost("kauditd retry queue overflow"); kfree_skb(skb); } /** * auditd_reset - Disconnect the auditd connection * @ac: auditd connection state * * Description: * Break the auditd/kauditd connection and move all the queued records into the * hold queue in case auditd reconnects. It is important to note that the @ac * pointer should never be dereferenced inside this function as it may be NULL * or invalid, you can only compare the memory address! If @ac is NULL then * the connection will always be reset. */ static void auditd_reset(const struct auditd_connection *ac) { unsigned long flags; struct sk_buff *skb; struct auditd_connection *ac_old; /* if it isn't already broken, break the connection */ spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); if (ac && ac != ac_old) { /* someone already registered a new auditd connection */ spin_unlock_irqrestore(&auditd_conn_lock, flags); return; } rcu_assign_pointer(auditd_conn, NULL); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) kauditd_hold_skb(skb, -ECONNREFUSED); } /** * auditd_send_unicast_skb - Send a record via unicast to auditd * @skb: audit record * * Description: * Send a skb to the audit daemon, returns positive/zero values on success and * negative values on failure; in all cases the skb will be consumed by this * function. If the send results in -ECONNREFUSED the connection with auditd * will be reset. This function may sleep so callers should not hold any locks * where this would cause a problem. */ static int auditd_send_unicast_skb(struct sk_buff *skb) { int rc; u32 portid; struct net *net; struct sock *sk; struct auditd_connection *ac; /* NOTE: we can't call netlink_unicast while in the RCU section so * take a reference to the network namespace and grab local * copies of the namespace, the sock, and the portid; the * namespace and sock aren't going to go away while we hold a * reference and if the portid does become invalid after the RCU * section netlink_unicast() should safely return an error */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); kfree_skb(skb); rc = -ECONNREFUSED; goto err; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); rc = netlink_unicast(sk, skb, portid, 0); put_net(net); if (rc < 0) goto err; return rc; err: if (ac && rc == -ECONNREFUSED) auditd_reset(ac); return rc; } /** * kauditd_send_queue - Helper for kauditd_thread to flush skb queues * @sk: the sending sock * @portid: the netlink destination * @queue: the skb queue to process * @retry_limit: limit on number of netlink unicast failures * @skb_hook: per-skb hook for additional processing * @err_hook: hook called if the skb fails the netlink unicast send * * Description: * Run through the given queue and attempt to send the audit records to auditd, * returns zero on success, negative values on failure. It is up to the caller * to ensure that the @sk is valid for the duration of this function. * */ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; struct sk_buff *skb = NULL; struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ skb_tail = skb_peek_tail(queue); while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) (*err_hook)(skb, -ECONNREFUSED); continue; } retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ continue; } else goto retry; } else { /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } return (rc >= 0 ? 0 : rc); } /* * kauditd_send_multicast_skb - Send a record to any multicast listeners * @skb: audit record * * Description: * Write a multicast message to anyone listening in the initial network * namespace. This function doesn't consume an skb as might be expected since * it has to copy it anyways. */ static void kauditd_send_multicast_skb(struct sk_buff *skb) { struct sk_buff *copy; struct sock *sock = audit_get_sk(&init_net); struct nlmsghdr *nlh; /* NOTE: we are not taking an additional reference for init_net since * we don't have to worry about it going away */ if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) return; /* * The seemingly wasteful skb_copy() rather than bumping the refcount * using skb_get() is necessary because non-standard mods are made to * the skb by the original kaudit unicast socket send routine. The * existing auditd daemon assumes this breakage. Fixing this would * require co-ordinating a change in the established protocol between * the kaudit kernel subsystem and the auditd userspace code. There is * no reason for new multicast clients to continue with this * non-compliance. */ copy = skb_copy(skb, GFP_KERNEL); if (!copy) return; nlh = nlmsg_hdr(copy); nlh->nlmsg_len = skb->len; nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL); } /** * kauditd_thread - Worker thread to send audit records to userspace * @dummy: unused */ static int kauditd_thread(void *dummy) { int rc; u32 portid = 0; struct net *net = NULL; struct sock *sk = NULL; struct auditd_connection *ac; #define UNICAST_RETRIES 5 set_freezable(); while (!kthread_should_stop()) { /* NOTE: see the lock comments in auditd_send_unicast_skb() */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); goto main_queue; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); /* attempt to flush the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_hold_queue, UNICAST_RETRIES, NULL, kauditd_rehold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } /* attempt to flush the retry queue */ rc = kauditd_send_queue(sk, portid, &audit_retry_queue, UNICAST_RETRIES, NULL, kauditd_hold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } main_queue: /* process the main queue - do the multicast send and attempt * unicast, dump failed record sends to the retry queue; if * sk == NULL due to previous failures we will just do the * multicast send and move the record to the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_queue, 1, kauditd_send_multicast_skb, (sk ? kauditd_retry_skb : kauditd_hold_skb)); if (ac && rc < 0) auditd_reset(ac); sk = NULL; /* drop our netns reference, no auditd sends past this line */ if (net) { put_net(net); net = NULL; } /* we have processed all the queues so wake everyone */ wake_up(&audit_backlog_wait); /* NOTE: we want to wake up if there is anything on the queue, * regardless of if an auditd is connected, as we need to * do the multicast send and rotate records from the * main queue to the retry/hold queues */ wait_event_freezable(kauditd_wait, (skb_queue_len(&audit_queue) ? 1 : 0)); } return 0; } int audit_send_list_thread(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; struct sock *sk = audit_get_sk(dest->net); /* wait for parent to finish and send an ACK */ audit_ctl_lock(); audit_ctl_unlock(); while ((skb = __skb_dequeue(&dest->q)) != NULL) netlink_unicast(sk, skb, dest->portid, 0); put_net(dest->net); kfree(dest); return 0; } struct sk_buff *audit_make_reply(int seq, int type, int done, int multi, const void *payload, int size) { struct sk_buff *skb; struct nlmsghdr *nlh; void *data; int flags = multi ? NLM_F_MULTI : 0; int t = done ? NLMSG_DONE : type; skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return NULL; nlh = nlmsg_put(skb, 0, seq, t, size, flags); if (!nlh) goto out_kfree_skb; data = nlmsg_data(nlh); memcpy(data, payload, size); return skb; out_kfree_skb: kfree_skb(skb); return NULL; } static void audit_free_reply(struct audit_reply *reply) { if (!reply) return; kfree_skb(reply->skb); if (reply->net) put_net(reply->net); kfree(reply); } static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; audit_ctl_lock(); audit_ctl_unlock(); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0); reply->skb = NULL; audit_free_reply(reply); return 0; } /** * audit_send_reply - send an audit reply message via netlink * @request_skb: skb of request we are replying to (used to target the reply) * @seq: sequence number * @type: audit message type * @done: done (last) flag * @multi: multi-part message flag * @payload: payload data * @size: payload size * * Allocates a skb, builds the netlink message, and sends it to the port id. */ static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { struct task_struct *tsk; struct audit_reply *reply; reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (!reply) return; reply->skb = audit_make_reply(seq, type, done, multi, payload, size); if (!reply->skb) goto err; reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); reply->portid = NETLINK_CB(request_skb).portid; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); if (IS_ERR(tsk)) goto err; return; err: audit_free_reply(reply); } /* * Check for appropriate CAP_AUDIT_ capabilities on incoming audit * control messages. */ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; /* Only support initial user namespace for now. */ /* * We return ECONNREFUSED because it tricks userspace into thinking * that audit was not configured into the kernel. Lots of users * configure their PAM stack (because that's what the distro does) * to reject login if unable to send messages to audit. If we return * ECONNREFUSED the PAM stack thinks the kernel does not have audit * configured in and will let login proceed. If we return EPERM * userspace will reject all logins. This should be removed when we * support non init namespaces!! */ if (current_user_ns() != &init_user_ns) return -ECONNREFUSED; switch (msg_type) { case AUDIT_LIST: case AUDIT_ADD: case AUDIT_DEL: return -EOPNOTSUPP; case AUDIT_GET: case AUDIT_SET: case AUDIT_GET_FEATURE: case AUDIT_SET_FEATURE: case AUDIT_LIST_RULES: case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: case AUDIT_SIGNAL_INFO: case AUDIT_TTY_GET: case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: /* Only support auditd and auditctl in initial pid namespace * for now. */ if (task_active_pid_ns(current) != &init_pid_ns) return -EPERM; if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ err = -EINVAL; } return err; } static void audit_log_common_recv_msg(struct audit_context *context, struct audit_buffer **ab, u16 msg_type) { uid_t uid = from_kuid(&init_user_ns, current_uid()); pid_t pid = task_tgid_nr(current); if (!audit_enabled && msg_type != AUDIT_USER_AVC) { *ab = NULL; return; } *ab = audit_log_start(context, GFP_KERNEL, msg_type); if (unlikely(!*ab)) return; audit_log_format(*ab, "pid=%d uid=%u ", pid, uid); audit_log_session_info(*ab); audit_log_task_context(*ab); } static inline void audit_log_user_recv_msg(struct audit_buffer **ab, u16 msg_type) { audit_log_common_recv_msg(NULL, ab, msg_type); } static int is_audit_feature_set(int i) { return af.features & AUDIT_FEATURE_TO_MASK(i); } static int audit_get_feature(struct sk_buff *skb) { u32 seq; seq = nlmsg_hdr(skb)->nlmsg_seq; audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature, u32 old_lock, u32 new_lock, int res) { struct audit_buffer *ab; if (audit_enabled == AUDIT_OFF) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE); if (!ab) return; audit_log_task_info(ab); audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); } static int audit_set_feature(struct audit_features *uaf) { int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); /* if there is ever a version 2 we should handle that here */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; new_lock = (uaf->lock | af.lock) & feature; old_lock = af.lock & feature; /* are we changing a locked feature? */ if (old_lock && (new_feature != old_feature)) { audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 0); return -EPERM; } } /* nothing invalid, do the changes */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; old_lock = af.lock & feature; new_lock = (uaf->lock | af.lock) & feature; if (new_feature != old_feature) audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 1); if (new_feature) af.features |= feature; else af.features &= ~feature; af.lock |= new_lock; } return 0; } static int audit_replace(struct pid *pid) { pid_t pvnr; struct sk_buff *skb; pvnr = pid_vnr(pid); skb = audit_make_reply(0, AUDIT_REPLACE, 0, 0, &pvnr, sizeof(pvnr)); if (!skb) return -ENOMEM; return auditd_send_unicast_skb(skb); } static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, bool *ack) { u32 seq; void *data; int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; struct lsm_context lsmctx = { NULL, 0, 0 }; err = audit_netlink_ok(skb, msg_type); if (err) return err; seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { struct audit_status s; memset(&s, 0, sizeof(s)); s.enabled = audit_enabled; s.failure = audit_failure; /* NOTE: use pid_vnr() so the PID is relative to the current * namespace */ s.pid = auditd_pid_vnr(); s.rate_limit = audit_rate_limit; s.backlog_limit = audit_backlog_limit; s.lost = atomic_read(&audit_lost); s.backlog = skb_queue_len(&audit_queue); s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL; s.backlog_wait_time = audit_backlog_wait_time; s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual); audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_SET: { struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_FAILURE) { err = audit_set_failure(s.failure); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_PID) { /* NOTE: we are using the vnr PID functions below * because the s.pid value is relative to the * namespace of the caller; at present this * doesn't matter much since you can really only * run auditd from the initial pid namespace, but * something to keep in mind if this changes */ pid_t new_pid = s.pid; pid_t auditd_pid; struct pid *req_pid = task_tgid(current); /* Sanity check - PID values must match. Setting * pid to 0 is how auditd ends auditing. */ if (new_pid && (new_pid != pid_vnr(req_pid))) return -EINVAL; /* test the auditd connection */ audit_replace(req_pid); auditd_pid = auditd_pid_vnr(); if (auditd_pid) { /* replacing a healthy auditd is not allowed */ if (new_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EEXIST; } /* only current auditd can unregister itself */ if (pid_vnr(req_pid) != auditd_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EACCES; } } if (new_pid) { /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, sock_net(NETLINK_CB(skb).sk), skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, err ? 0 : 1); if (err) return err; /* try to process any backlog */ wake_up_interruptible(&kauditd_wait); } else { if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, 1); /* unregister the auditd connection */ auditd_reset(NULL); } } if (s.mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(s.rate_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) { err = audit_set_backlog_limit(s.backlog_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) { if (sizeof(s) > (size_t)nlh->nlmsg_len) return -EINVAL; if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME) return -EINVAL; err = audit_set_backlog_wait_time(s.backlog_wait_time); if (err < 0) return err; } if (s.mask == AUDIT_STATUS_LOST) { u32 lost = atomic_xchg(&audit_lost, 0); audit_log_config_change("lost", 0, lost, 1); return lost; } if (s.mask == AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) { u32 actual = atomic_xchg(&audit_backlog_wait_time_actual, 0); audit_log_config_change("backlog_wait_time_actual", 0, actual, 1); return actual; } break; } case AUDIT_GET_FEATURE: err = audit_get_feature(skb); if (err) return err; break; case AUDIT_SET_FEATURE: if (data_len < sizeof(struct audit_features)) return -EINVAL; err = audit_set_feature(data); if (err) return err; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; /* exit early if there isn't at least one character to print */ if (data_len < 2) return -EINVAL; err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ char *str = data; err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); if (err) break; } audit_log_user_recv_msg(&ab, msg_type); if (msg_type != AUDIT_USER_TTY) { /* ensure NULL termination */ str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, str); } else { audit_log_format(ab, " data="); if (str[data_len - 1] == '\0') data_len--; audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=%s audit_enabled=%d res=0", msg_type == AUDIT_ADD_RULE ? "add_rule" : "remove_rule", audit_enabled); audit_log_end(ab); return -EPERM; } err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=trim res=1"); audit_log_end(ab); break; case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; size_t msglen = data_len; char *old, *new; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; memcpy(sizes, bufp, 2 * sizeof(u32)); bufp += 2 * sizeof(u32); msglen -= 2 * sizeof(u32); old = audit_unpack_string(&bufp, &msglen, sizes[0]); if (IS_ERR(old)) { err = PTR_ERR(old); break; } new = audit_unpack_string(&bufp, &msglen, sizes[1]); if (IS_ERR(new)) { err = PTR_ERR(new); kfree(old); break; } /* OK, here comes... */ err = audit_tag_tree(old, new); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=make_equiv old="); audit_log_untrustedstring(ab, old); audit_log_format(ab, " new="); audit_log_untrustedstring(ab, new); audit_log_format(ab, " res=%d", !err); audit_log_end(ab); kfree(old); kfree(new); break; } case AUDIT_SIGNAL_INFO: if (lsmprop_is_set(&audit_sig_lsm)) { err = security_lsmprop_to_secctx(&audit_sig_lsm, &lsmctx); if (err < 0) return err; } sig_data = kmalloc(struct_size(sig_data, ctx, lsmctx.len), GFP_KERNEL); if (!sig_data) { if (lsmprop_is_set(&audit_sig_lsm)) security_release_secctx(&lsmctx); return -ENOMEM; } sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; if (lsmprop_is_set(&audit_sig_lsm)) { memcpy(sig_data->ctx, lsmctx.context, lsmctx.len); security_release_secctx(&lsmctx); } audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, struct_size(sig_data, ctx, lsmctx.len)); kfree(sig_data); break; case AUDIT_TTY_GET: { struct audit_tty_status s; unsigned int t; t = READ_ONCE(current->signal->audit_tty); s.enabled = t & AUDIT_TTY_ENABLE; s.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { struct audit_tty_status s, old; struct audit_buffer *ab; unsigned int t; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) err = -EINVAL; if (err) t = READ_ONCE(current->signal->audit_tty); else { t = s.enabled | (-s.log_passwd & AUDIT_TTY_LOG_PASSWD); t = xchg(¤t->signal->audit_tty, t); } old.enabled = t & AUDIT_TTY_ENABLE; old.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d" " old-log_passwd=%d new-log_passwd=%d res=%d", old.enabled, s.enabled, old.log_passwd, s.log_passwd, !err); audit_log_end(ab); break; } default: err = -EINVAL; break; } return err < 0 ? err : 0; } /** * audit_receive - receive messages from a netlink control socket * @skb: the message buffer * * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned */ int len; int err; nlh = nlmsg_hdr(skb); len = skb->len; audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { ack = nlh->nlmsg_flags & NLM_F_ACK; err = audit_receive_msg(skb, nlh, &ack); /* send an ack if the user asked for one and audit_receive_msg * didn't already do it, or if there was an error. */ if (ack || err) netlink_ack(skb, nlh, err, NULL); nlh = nlmsg_next(nlh, &len); } audit_ctl_unlock(); /* can't block with the ctrl lock, so penalize the sender now */ if (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { DECLARE_WAITQUEUE(wait, current); /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(audit_backlog_wait_time); remove_wait_queue(&audit_backlog_wait, &wait); } } /* Log information about who is connecting to the audit multicast socket */ static void audit_log_multicast(int group, const char *op, int err) { const struct cred *cred; struct tty_struct *tty; char comm[sizeof(current->comm)]; struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER); if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u", task_tgid_nr(current), from_kuid(&init_user_ns, cred->uid), from_kuid(&init_user_ns, audit_get_loginuid(current)), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_task_context(ab); /* subj= */ audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); /* exe= */ audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err); audit_log_end(ab); } /* Run custom bind function on netlink socket group connect or bind requests. */ static int audit_multicast_bind(struct net *net, int group) { int err = 0; if (!capable(CAP_AUDIT_READ)) err = -EPERM; audit_log_multicast(group, "connect", err); return err; } static void audit_multicast_unbind(struct net *net, int group) { audit_log_multicast(group, "disconnect", 0); } static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, .bind = audit_multicast_bind, .unbind = audit_multicast_unbind, .flags = NL_CFG_F_NONROOT_RECV, .groups = AUDIT_NLGRP_MAX, }; struct audit_net *aunet = net_generic(net, audit_net_id); aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); if (aunet->sk == NULL) { audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } /* limit the timeout in case auditd is blocked/stopped */ aunet->sk->sk_sndtimeo = HZ / 10; return 0; } static void __net_exit audit_net_exit(struct net *net) { struct audit_net *aunet = net_generic(net, audit_net_id); /* NOTE: you would think that we would want to check the auditd * connection and potentially reset it here if it lives in this * namespace, but since the auditd connection tracking struct holds a * reference to this namespace (see auditd_set()) we are only ever * going to get here after that connection has been released */ netlink_kernel_release(aunet->sk); } static struct pernet_operations audit_net_ops __net_initdata = { .init = audit_net_init, .exit = audit_net_exit, .id = &audit_net_id, .size = sizeof(struct audit_net), }; /* Initialize audit support at boot time. */ static int __init audit_init(void) { int i; if (audit_initialized == AUDIT_DISABLED) return 0; audit_buffer_cache = KMEM_CACHE(audit_buffer, SLAB_PANIC); skb_queue_head_init(&audit_queue); skb_queue_head_init(&audit_retry_queue); skb_queue_head_init(&audit_hold_queue); for (i = 0; i < AUDIT_INODE_BUCKETS; i++) INIT_LIST_HEAD(&audit_inode_hash[i]); mutex_init(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = NULL; pr_info("initializing netlink subsys (%s)\n", str_enabled_disabled(audit_default)); register_pernet_subsys(&audit_net_ops); audit_initialized = AUDIT_INITIALIZED; kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); if (IS_ERR(kauditd_task)) { int err = PTR_ERR(kauditd_task); panic("audit: failed to start the kauditd thread (%d)\n", err); } audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "state=initialized audit_enabled=%u res=1", audit_enabled); return 0; } postcore_initcall(audit_init); /* * Process kernel command-line parameter at boot time. * audit={0|off} or audit={1|on}. */ static int __init audit_enable(char *str) { if (!strcasecmp(str, "off") || !strcmp(str, "0")) audit_default = AUDIT_OFF; else if (!strcasecmp(str, "on") || !strcmp(str, "1")) audit_default = AUDIT_ON; else { pr_err("audit: invalid 'audit' parameter value (%s)\n", str); audit_default = AUDIT_ON; } if (audit_default == AUDIT_OFF) audit_initialized = AUDIT_DISABLED; if (audit_set_enabled(audit_default)) pr_err("audit: error setting audit state (%d)\n", audit_default); pr_info("%s\n", audit_default ? "enabled (after initialization)" : "disabled (until reboot)"); return 1; } __setup("audit=", audit_enable); /* Process kernel command-line parameter at boot time. * audit_backlog_limit=<n> */ static int __init audit_backlog_limit_set(char *str) { u32 audit_backlog_limit_arg; pr_info("audit_backlog_limit: "); if (kstrtouint(str, 0, &audit_backlog_limit_arg)) { pr_cont("using default of %u, unable to parse %s\n", audit_backlog_limit, str); return 1; } audit_backlog_limit = audit_backlog_limit_arg; pr_cont("%d\n", audit_backlog_limit); return 1; } __setup("audit_backlog_limit=", audit_backlog_limit_set); static void audit_buffer_free(struct audit_buffer *ab) { if (!ab) return; kfree_skb(ab->skb); kmem_cache_free(audit_buffer_cache, ab); } static struct audit_buffer *audit_buffer_alloc(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; ab = kmem_cache_alloc(audit_buffer_cache, gfp_mask); if (!ab) return NULL; ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); if (!ab->skb) goto err; if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0)) goto err; ab->ctx = ctx; ab->gfp_mask = gfp_mask; return ab; err: audit_buffer_free(ab); return NULL; } /** * audit_serial - compute a serial number for the audit record * * Compute a serial number for the audit record. Audit records are * written to user-space as soon as they are generated, so a complete * audit record may be written in several pieces. The timestamp of the * record and this serial number are used by the user-space tools to * determine which pieces belong to the same audit record. The * (timestamp,serial) tuple is unique for each syscall and is live from * syscall entry to syscall exit. * * NOTE: Another possibility is to store the formatted records off the * audit context (for those records that have a context), and emit them * all at syscall exit. However, this could delay the reporting of * significant errors until syscall exit (or never, if the system * halts). */ unsigned int audit_serial(void) { static atomic_t serial = ATOMIC_INIT(0); return atomic_inc_return(&serial); } static inline void audit_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { ktime_get_coarse_real_ts64(t); *serial = audit_serial(); } } /** * audit_log_start - obtain an audit buffer * @ctx: audit_context (may be NULL) * @gfp_mask: type of allocation * @type: audit message type * * Returns audit_buffer pointer on success or NULL on error. * * Obtain an audit buffer. This routine does locking to obtain the * audit buffer, but then no locking is required for calls to * audit_log_*format. If the task (ctx) is a task that is currently in a * syscall, then the syscall is marked as auditable and an audit record * will be written at syscall exit. If there is no associated task, then * task context (ctx) should be NULL. */ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; struct timespec64 t; unsigned int serial; if (audit_initialized != AUDIT_INITIALIZED) return NULL; if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE))) return NULL; /* NOTE: don't ever fail/sleep on these two conditions: * 1. auditd generated record - since we need auditd to drain the * queue; also, when we are checking for auditd, compare PIDs using * task_tgid_vnr() since auditd_pid is set in audit_receive_msg() * using a PID anchored in the caller's namespace * 2. generator holding the audit_cmd_mutex - we don't want to block * while holding the mutex, although we do penalize the sender * later in audit_receive() when it is safe to block */ if (!(auditd_test_task(current) || audit_ctl_owner_current())) { long stime = audit_backlog_wait_time; while (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); /* sleep if we are allowed and we haven't exhausted our * backlog wait limit */ if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) { long rtime = stime; DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); stime = schedule_timeout(rtime); atomic_add(rtime - stime, &audit_backlog_wait_time_actual); remove_wait_queue(&audit_backlog_wait, &wait); } else { if (audit_rate_check() && printk_ratelimit()) pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n", skb_queue_len(&audit_queue), audit_backlog_limit); audit_log_lost("backlog limit exceeded"); return NULL; } } } ab = audit_buffer_alloc(ctx, gfp_mask, type); if (!ab) { audit_log_lost("out of memory in audit_log_start"); return NULL; } audit_get_stamp(ab->ctx, &t, &serial); /* cancel dummy context to enable supporting records */ if (ctx) ctx->dummy = 0; audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); return ab; } /** * audit_expand - expand skb in the audit buffer * @ab: audit_buffer * @extra: space to add at tail of the skb * * Returns 0 (no space) on failed expansion, or available space if * successful. */ static inline int audit_expand(struct audit_buffer *ab, int extra) { struct sk_buff *skb = ab->skb; int oldtail = skb_tailroom(skb); int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask); int newtail = skb_tailroom(skb); if (ret < 0) { audit_log_lost("out of memory in audit_expand"); return 0; } skb->truesize += newtail - oldtail; return newtail; } /* * Format an audit message into the audit buffer. If there isn't enough * room in the audit buffer, more room will be allocated and vsnprint * will be called a second time. Currently, we assume that a printk * can't format message larger than 1024 bytes, so we don't either. */ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, va_list args) { int len, avail; struct sk_buff *skb; va_list args2; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); if (avail == 0) { avail = audit_expand(ab, AUDIT_BUFSIZ); if (!avail) goto out; } va_copy(args2, args); len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args); if (len >= avail) { /* The printk buffer is 1024 bytes long, so if we get * here and AUDIT_BUFSIZ is at least 1024, then we can * log everything that printk could have logged. */ avail = audit_expand(ab, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) goto out_va_end; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } if (len > 0) skb_put(skb, len); out_va_end: va_end(args2); out: return; } /** * audit_log_format - format a message into the audit buffer. * @ab: audit_buffer * @fmt: format string * @...: optional parameters matching @fmt string * * All the work is done in audit_log_vformat. */ void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { va_list args; if (!ab) return; va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); } /** * audit_log_n_hex - convert a buffer to hex and append it to the audit skb * @ab: the audit_buffer * @buf: buffer to convert to hex * @len: length of @buf to be converted * * No return value; failure to expand is silently ignored. * * This function will take the passed buf and convert it into a string of * ascii hex digits. The new string is placed onto the skb. */ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { int i, avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = len<<1; if (new_len >= avail) { /* Round the buffer request up to the next multiple */ new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); for (i = 0; i < len; i++) ptr = hex_byte_pack_upper(ptr, buf[i]); *ptr = 0; skb_put(skb, len << 1); /* new string is twice the old string */ } /* * Format a string of no more than slen characters into the audit buffer, * enclosed in quote marks. */ void audit_log_n_string(struct audit_buffer *ab, const char *string, size_t slen) { int avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = slen + 3; /* enclosing quotes + null terminator */ if (new_len > avail) { avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); *ptr++ = '"'; memcpy(ptr, string, slen); ptr += slen; *ptr++ = '"'; *ptr = 0; skb_put(skb, slen + 2); /* don't include null terminator */ } /** * audit_string_contains_control - does a string need to be logged in hex * @string: string to be checked * @len: max length of the string to check */ bool audit_string_contains_control(const char *string, size_t len) { const unsigned char *p; for (p = string; p < (const unsigned char *)string + len; p++) { if (*p == '"' || *p < 0x21 || *p > 0x7e) return true; } return false; } /** * audit_log_n_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @string: string to be logged * @len: length of string (not including trailing null) * * This code will escape a string that is passed to it if the string * contains a control character, unprintable character, double quote mark, * or a space. Unescaped strings will start and end with a double quote mark. * Strings that are escaped are printed in hex (2 digits per char). * * The caller specifies the number of characters in the string to log, which may * or may not be the entire string. */ void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t len) { if (audit_string_contains_control(string, len)) audit_log_n_hex(ab, string, len); else audit_log_n_string(ab, string, len); } /** * audit_log_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @string: string to be logged * * Same as audit_log_n_untrustedstring(), except that strlen is used to * determine string length. */ void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { audit_log_n_untrustedstring(ab, string, strlen(string)); } /* This is a helper-function to print the escaped d_path */ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { char *p, *pathname; if (prefix) audit_log_format(ab, "%s", prefix); /* We will allow 11 spaces for ' (deleted)' to be appended */ pathname = kmalloc(PATH_MAX+11, ab->gfp_mask); if (!pathname) { audit_log_format(ab, "\"<no_memory>\""); return; } p = d_path(path, pathname, PATH_MAX+11); if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */ /* FIXME: can we save some information here? */ audit_log_format(ab, "\"<too_long>\""); } else audit_log_untrustedstring(ab, p); kfree(pathname); } void audit_log_session_info(struct audit_buffer *ab) { unsigned int sessionid = audit_get_sessionid(current); uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current)); audit_log_format(ab, "auid=%u ses=%u", auid, sessionid); } void audit_log_key(struct audit_buffer *ab, char *key) { audit_log_format(ab, " key="); if (key) audit_log_untrustedstring(ab, key); else audit_log_format(ab, "(null)"); } int audit_log_task_context(struct audit_buffer *ab) { struct lsm_prop prop; struct lsm_context ctx; int error; security_current_getlsmprop_subj(&prop); if (!lsmprop_is_set(&prop)) return 0; error = security_lsmprop_to_secctx(&prop, &ctx); if (error < 0) { if (error != -EINVAL) goto error_path; return 0; } audit_log_format(ab, " subj=%s", ctx.context); security_release_secctx(&ctx); return 0; error_path: audit_panic("error in audit_log_task_context"); return error; } EXPORT_SYMBOL(audit_log_task_context); void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm) { struct file *exe_file; if (!mm) goto out_null; exe_file = get_mm_exe_file(mm); if (!exe_file) goto out_null; audit_log_d_path(ab, " exe=", &exe_file->f_path); fput(exe_file); return; out_null: audit_log_format(ab, " exe=(null)"); } struct tty_struct *audit_get_tty(void) { struct tty_struct *tty = NULL; unsigned long flags; spin_lock_irqsave(¤t->sighand->siglock, flags); if (current->signal) tty = tty_kref_get(current->signal->tty); spin_unlock_irqrestore(¤t->sighand->siglock, flags); return tty; } void audit_put_tty(struct tty_struct *tty) { tty_kref_put(tty); } void audit_log_task_info(struct audit_buffer *ab) { const struct cred *cred; char comm[sizeof(current->comm)]; struct tty_struct *tty; if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", task_ppid_nr(current), task_tgid_nr(current), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, cred->uid), from_kgid(&init_user_ns, cred->gid), from_kuid(&init_user_ns, cred->euid), from_kuid(&init_user_ns, cred->suid), from_kuid(&init_user_ns, cred->fsuid), from_kgid(&init_user_ns, cred->egid), from_kgid(&init_user_ns, cred->sgid), from_kgid(&init_user_ns, cred->fsgid), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); audit_log_task_context(ab); } EXPORT_SYMBOL(audit_log_task_info); /** * audit_log_path_denied - report a path restriction denial * @type: audit message type (AUDIT_ANOM_LINK, AUDIT_ANOM_CREAT, etc) * @operation: specific operation name */ void audit_log_path_denied(int type, const char *operation) { struct audit_buffer *ab; if (!audit_enabled || audit_dummy_context()) return; /* Generate log with subject, operation, outcome. */ ab = audit_log_start(audit_context(), GFP_KERNEL, type); if (!ab) return; audit_log_format(ab, "op=%s", operation); audit_log_task_info(ab); audit_log_format(ab, " res=0"); audit_log_end(ab); } /* global counter which is incremented every time something logs in */ static atomic_t session_id = ATOMIC_INIT(0); static int audit_set_loginuid_perm(kuid_t loginuid) { /* if we are unset, we don't need privs */ if (!audit_loginuid_set(current)) return 0; /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) return -EPERM; /* it is set, you need permission */ if (!capable(CAP_AUDIT_CONTROL)) return -EPERM; /* reject if this is not an unset and we don't allow that */ if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) return -EPERM; return 0; } static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, unsigned int oldsessionid, unsigned int sessionid, int rc) { struct audit_buffer *ab; uid_t uid, oldloginuid, loginuid; struct tty_struct *tty; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_LOGIN); if (!ab) return; uid = from_kuid(&init_user_ns, task_uid(current)); oldloginuid = from_kuid(&init_user_ns, koldloginuid); loginuid = from_kuid(&init_user_ns, kloginuid); tty = audit_get_tty(); audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid); audit_log_task_context(ab); audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", oldloginuid, loginuid, tty ? tty_name(tty) : "(none)", oldsessionid, sessionid, !rc); audit_put_tty(tty); audit_log_end(ab); } /** * audit_set_loginuid - set current task's loginuid * @loginuid: loginuid value * * Returns 0. * * Called (set) from fs/proc/base.c::proc_loginuid_write(). */ int audit_set_loginuid(kuid_t loginuid) { unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; kuid_t oldloginuid; int rc; oldloginuid = audit_get_loginuid(current); oldsessionid = audit_get_sessionid(current); rc = audit_set_loginuid_perm(loginuid); if (rc) goto out; /* are we setting or clearing? */ if (uid_valid(loginuid)) { sessionid = (unsigned int)atomic_inc_return(&session_id); if (unlikely(sessionid == AUDIT_SID_UNSET)) sessionid = (unsigned int)atomic_inc_return(&session_id); } current->sessionid = sessionid; current->loginuid = loginuid; out: audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); return rc; } /** * audit_signal_info - record signal info for shutting down audit subsystem * @sig: signal value * @t: task being signaled * * If the audit subsystem is being terminated, record the task (pid) * and uid that is doing that. */ int audit_signal_info(int sig, struct task_struct *t) { kuid_t uid = current_uid(), auid; if (auditd_test_task(t) && (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2)) { audit_sig_pid = task_tgid_nr(current); auid = audit_get_loginuid(current); if (uid_valid(auid)) audit_sig_uid = auid; else audit_sig_uid = uid; security_current_getlsmprop_subj(&audit_sig_lsm); } return audit_signal_info_syscall(t); } /** * audit_log_end - end one audit record * @ab: the audit_buffer * * We can not do a netlink send inside an irq context because it blocks (last * arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a * queue and a kthread is scheduled to remove them from the queue outside the * irq context. May be called in any context. */ void audit_log_end(struct audit_buffer *ab) { struct sk_buff *skb; struct nlmsghdr *nlh; if (!ab) return; if (audit_rate_check()) { skb = ab->skb; ab->skb = NULL; /* setup the netlink header, see the comments in * kauditd_send_multicast_skb() for length quirks */ nlh = nlmsg_hdr(skb); nlh->nlmsg_len = skb->len - NLMSG_HDRLEN; /* queue the netlink packet and poke the kauditd thread */ skb_queue_tail(&audit_queue, skb); wake_up_interruptible(&kauditd_wait); } else audit_log_lost("rate limit exceeded"); audit_buffer_free(ab); } /** * audit_log - Log an audit record * @ctx: audit context * @gfp_mask: type of allocation * @type: audit message type * @fmt: format string to use * @...: variable parameters matching the format string * * This is a convenience function that calls audit_log_start, * audit_log_vformat, and audit_log_end. It may be called * in any context. */ void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { struct audit_buffer *ab; va_list args; ab = audit_log_start(ctx, gfp_mask, type); if (ab) { va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); audit_log_end(ab); } } EXPORT_SYMBOL(audit_log_start); EXPORT_SYMBOL(audit_log_end); EXPORT_SYMBOL(audit_log_format); EXPORT_SYMBOL(audit_log); |
| 38 677 622 224 565 312 278 45 45 232 11 170 261 6 173 525 325 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/container_of.h> #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <asm/barrier.h> /* * Circular doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } #ifdef CONFIG_LIST_HARDENED #ifdef CONFIG_DEBUG_LIST # define __list_valid_slowpath #else # define __list_valid_slowpath __cold __preserve_most #endif /* * Performs the full set of list corruption checks before __list_add(). * On list corruption reports a warning, and returns false. */ extern bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new, struct list_head *prev, struct list_head *next); /* * Performs list corruption checks before __list_add(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_add_valid_or_report(). */ static __always_inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { /* * With the hardening version, elide checking if next and prev * are NULL, since the immediate dereference of them below would * result in a fault if NULL. * * With the reduced set of checks, we can afford to inline the * checks, which also gives the compiler a chance to elide some * of them completely if they can be proven at compile-time. If * one of the pre-conditions does not hold, the slow-path will * show a report which pre-condition failed. */ if (likely(next->prev == prev && prev->next == next && new != prev && new != next)) return true; ret = false; } ret &= __list_add_valid_or_report(new, prev, next); return ret; } /* * Performs the full set of list corruption checks before __list_del_entry(). * On list corruption reports a warning, and returns false. */ extern bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry); /* * Performs list corruption checks before __list_del_entry(). Returns false if a * corruption is detected, true otherwise. * * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking * inline to catch non-faulting corruptions, and only if a corruption is * detected calls the reporting function __list_del_entry_valid_or_report(). */ static __always_inline bool __list_del_entry_valid(struct list_head *entry) { bool ret = true; if (!IS_ENABLED(CONFIG_DEBUG_LIST)) { struct list_head *prev = entry->prev; struct list_head *next = entry->next; /* * With the hardening version, elide checking if next and prev * are NULL, LIST_POISON1 or LIST_POISON2, since the immediate * dereference of them below would result in a fault. */ if (likely(prev->next == entry && next->prev == entry)) return true; ret = false; } ret &= __list_del_entry_valid_or_report(entry); return ret; } #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_is_head - tests whether @list is the list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_head(const struct list_head *list, const struct list_head *head) { return list == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_next_entry_circular - get the next element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the last element (return the first element). * Note, that list is expected to be not empty. */ #define list_next_entry_circular(pos, head, member) \ (list_is_last(&(pos)->member, head) ? \ list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_prev_entry_circular - get the prev element in list * @pos: the type * to cursor. * @head: the list head to take the element from. * @member: the name of the list_head within the struct. * * Wraparound if pos is the first element (return the last element). * Note, that list is expected to be not empty. */ #define list_prev_entry_circular(pos, head, member) \ (list_is_first(&(pos)->member, head) ? \ list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_rcu - Iterate over a list in an RCU-safe fashion * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_rcu(pos, head) \ for (pos = rcu_dereference((head)->next); \ !list_is_head(pos, (head)); \ pos = rcu_dereference(pos->next)) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; \ !list_is_head(pos, (head)); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** * list_count_nodes - count nodes in the list * @head: the head for your list. */ static inline size_t list_count_nodes(struct list_head *head) { struct list_head *pos; size_t count = 0; list_for_each(pos, head) count++; return count; } /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ list_is_head(&pos->member, (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } /** * hlist_splice_init() - move all entries from one list to another * @from: hlist_head from which entries will be moved * @last: last entry on the @from list * @to: hlist_head to which entries will be moved * * @to can be empty, @from must contain at least @last. */ static inline void hlist_splice_init(struct hlist_head *from, struct hlist_node *last, struct hlist_head *to) { if (to->first) to->first->pprev = &last->next; last->next = to->first; to->first = from->first; from->first->pprev = &to->first; from->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) /** * hlist_count_nodes - count nodes in the hlist * @head: the head for your hlist. */ static inline size_t hlist_count_nodes(struct hlist_head *head) { struct hlist_node *pos; size_t count = 0; hlist_for_each(pos, head) count++; return count; } #endif |
| 139 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_H #define __ASM_MMU_H #include <asm/cputype.h> #define MMCF_AARCH32 0x1 /* mm context flag for AArch32 executables */ #define USER_ASID_BIT 48 #define USER_ASID_FLAG (UL(1) << USER_ASID_BIT) #define TTBR_ASID_MASK (UL(0xffff) << 48) #ifndef __ASSEMBLY__ #include <linux/refcount.h> #include <asm/cpufeature.h> typedef struct { atomic64_t id; #ifdef CONFIG_COMPAT void *sigpage; #endif refcount_t pinned; void *vdso; unsigned long flags; u8 pkey_allocation_map; } mm_context_t; /* * We use atomic64_read() here because the ASID for an 'mm_struct' can * be reallocated when scheduling one of its threads following a * rollover event (see new_context() and flush_context()). In this case, * a concurrent TLBI (e.g. via try_to_unmap_one() and ptep_clear_flush()) * may use a stale ASID. This is fine in principle as the new ASID is * guaranteed to be clean in the TLB, but the TLBI routines have to take * care to handle the following race: * * CPU 0 CPU 1 CPU 2 * * // ptep_clear_flush(mm) * xchg_relaxed(pte, 0) * DSB ISHST * old = ASID(mm) * | <rollover> * | new = new_context(mm) * \-----------------> atomic_set(mm->context.id, new) * cpu_switch_mm(mm) * // Hardware walk of pte using new ASID * TLBI(old) * * In this scenario, the barrier on CPU 0 and the dependency on CPU 1 * ensure that the page-table walker on CPU 1 *must* see the invalid PTE * written by CPU 0. */ #define ASID(mm) (atomic64_read(&(mm)->context.id) & 0xffff) static inline bool arm64_kernel_unmapped_at_el0(void) { return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0); } extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); /* * This check is triggered during the early boot before the cpufeature * is initialised. Checking the status on the local CPU allows the boot * CPU to detect the need for non-global mappings and thus avoiding a * pagetable re-write after all the CPUs are booted. This check will be * anyway run on individual CPUs, allowing us to get the consistent * state once the SMP CPUs are up and thus make the switch to non-global * mappings if required. */ static inline bool kaslr_requires_kpti(void) { /* * E0PD does a similar job to KPTI so can be used instead * where available. */ if (IS_ENABLED(CONFIG_ARM64_E0PD)) { u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); if (cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_E0PD_SHIFT)) return false; } /* * Systems affected by Cavium erratum 24756 are incompatible * with KPTI. */ if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { extern const struct midr_range cavium_erratum_27456_cpus[]; if (is_midr_in_range_list(read_cpuid_id(), cavium_erratum_27456_cpus)) return false; } return true; } #endif /* !__ASSEMBLY__ */ #endif |
| 9 10 1 1 1 9 9 9 8 8 8 9 9 9 9 9 10 10 9 10 10 1 9 9 9 9 9 1 1 1 9 9 9 1 1 1 1 1 47 43 47 7 11 11 15 24 11 23 1 4 29 3 41 7 3 5 4 12 5 7 23 23 11 21 11 23 27 27 27 12 21 11 56 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC MMIO handling functions */ #include <linux/bitops.h> #include <linux/bsearch.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/iodev.h> #include <kvm/arm_arch_timer.h> #include <kvm/arm_vgic.h> #include "vgic.h" #include "vgic-mmio.h" unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return 0; } unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return -1UL; } void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ } int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ return 0; } unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->group) value |= BIT(i); vgic_put_irq(vcpu->kvm, irq); } return value; } static void vgic_update_vsgi(struct vgic_irq *irq) { WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); } void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } else { vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } vgic_put_irq(vcpu->kvm, irq); } } /* * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value * of the enabled bit, so there is only one function for both here. */ unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->enabled) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return value; } void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { if (!irq->enabled) { struct irq_data *data; irq->enabled = true; data = &irq_to_desc(irq->host_irq)->irq_data; while (irqd_irq_disabled(data)) enable_irq(irq->host_irq); } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } else if (vgic_irq_is_mapped_level(irq)) { bool was_high = irq->line_level; /* * We need to update the state of the interrupt because * the guest might have changed the state of the device * while the interrupt was disabled at the VGIC level. */ irq->line_level = vgic_get_phys_line_level(irq); /* * Deactivate the physical interrupt so the GIC will let * us know when it is asserted again. */ if (!irq->active && was_high && !irq->line_level) vgic_irq_set_phys_active(irq, false); } irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) disable_irq_nosync(irq->host_irq); irq->enabled = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } return 0; } int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } return 0; } static unsigned long __read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); unsigned long flags; bool val; /* * When used from userspace with a GICv3 model: * * Pending state of interrupt is latched in pending_latch * variable. Userspace will save and restore pending state * and line_level separately. * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst * for handling of ISPENDR and ICPENDR. */ raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; val = false; err = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &val); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); } else if (!is_user && vgic_irq_is_mapped_level(irq)) { val = vgic_get_phys_line_level(irq); } else { switch (vcpu->kvm->arch.vgic.vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V3: if (is_user) { val = irq->pending_latch; break; } fallthrough; default: val = irq_is_pending(irq); break; } } value |= ((u32)val << i); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } return value; } unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __read_pending(vcpu, addr, len, false); } unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __read_pending(vcpu, addr, len, true); } static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2); } static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); /* GICD_ISPENDR0 SGI bits are WI when written from the guest. */ if (is_vgic_v2_sgi(vcpu, irq) && !is_user) { vgic_put_irq(vcpu->kvm, irq); continue; } raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * GICv2 SGIs are terribly broken. We can't restore * the source of the interrupt, so just pick the vcpu * itself as the source... */ if (is_vgic_v2_sgi(vcpu, irq)) irq->source |= BIT(vcpu->vcpu_id); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* HW SGI? Ask the GIC to inject it */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } irq->pending_latch = true; if (irq->hw && !is_user) vgic_irq_set_phys_active(irq, true); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __set_pending(vcpu, addr, len, val, false); } int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __set_pending(vcpu, addr, len, val, true); return 0; } /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { irq->pending_latch = false; /* * We don't want the guest to effectively mask the physical * interrupt by doing a write to SPENDR followed by a write to * CPENDR for HW interrupts, so we clear the active state on * the physical side if the virtual interrupt is not active. * This may lead to taking an additional interrupt on the * host, but that should not be a problem as the worst that * can happen is an additional vgic injection. We also clear * the pending state to maintain proper semantics for edge HW * interrupts. */ vgic_irq_set_phys_pending(irq, false); if (!irq->active) vgic_irq_set_phys_active(irq, false); } static void __clear_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); /* GICD_ICPENDR0 SGI bits are WI when written from the guest. */ if (is_vgic_v2_sgi(vcpu, irq) && !is_user) { vgic_put_irq(vcpu->kvm, irq); continue; } raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * More fun with GICv2 SGIs! If we're clearing one of them * from userspace, which source vcpu to clear? Let's not * even think of it, and blow the whole set. */ if (is_vgic_v2_sgi(vcpu, irq)) irq->source = 0; if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* HW SGI? Ask the GIC to clear its pending bit */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, false); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } if (irq->hw && !is_user) vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __clear_pending(vcpu, addr, len, val, false); } int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __clear_pending(vcpu, addr, len, val, true); return 0; } /* * If we are fiddling with an IRQ's active state, we have to make sure the IRQ * is not queued on some running VCPU's LRs, because then the change to the * active state can be overwritten when the VCPU's state is synced coming back * from the guest. * * For shared interrupts as well as GICv3 private interrupts accessed from the * non-owning CPU, we have to stop all the VCPUs because interrupts can be * migrated while we don't hold the IRQ locks and we don't want to be chasing * moving targets. * * For GICv2 private interrupts we don't have to do anything because * userspace accesses to the VGIC state already require all VCPUs to be * stopped, and only the VCPU itself can modify its private interrupts * active state, which guarantees that the VCPU is not running. */ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) { if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_halt_guest(vcpu->kvm); } /* See vgic_access_active_prepare */ static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) { if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_resume_guest(vcpu->kvm); } static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); /* * Even for HW interrupts, don't evaluate the HW state as * all the guest is interested in is the virtual state. */ if (irq->active) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return value; } unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 val; mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); val = __vgic_mmio_read_active(vcpu, addr, len); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); return val; } unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __vgic_mmio_read_active(vcpu, addr, len); } /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) { if (is_uaccess) return; irq->active = active; vgic_irq_set_phys_active(irq, active); } static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active) { unsigned long flags; struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu(); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* * GICv4.1 VSGI feature doesn't track an active state, * so let's not kid ourselves, there is nothing we can * do here. */ irq->active = false; } else { u32 model = vcpu->kvm->arch.vgic.vgic_model; u8 active_source; irq->active = active; /* * The GICv2 architecture indicates that the source CPUID for * an SGI should be provided during an EOI which implies that * the active state is stored somewhere, but at the same time * this state is not architecturally exposed anywhere and we * have no way of knowing the right source. * * This may lead to a VCPU not being able to receive * additional instances of a particular SGI after migration * for a GICv2 VM on some GIC implementations. Oh well. */ active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0; if (model == KVM_DEV_TYPE_ARM_VGIC_V2 && active && vgic_irq_is_sgi(irq->intid)) irq->active_source = active_source; } if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); vgic_mmio_change_active(vcpu, irq, false); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __vgic_mmio_write_cactive(vcpu, addr, len, val); return 0; } static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); vgic_mmio_change_active(vcpu, irq, true); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __vgic_mmio_write_sactive(vcpu, addr, len, val); return 0; } unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 8); int i; u64 val = 0; for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); val |= (u64)irq->priority << (i * 8); vgic_put_irq(vcpu->kvm, irq); } return val; } /* * We currently don't handle changing the priority of an interrupt that * is already pending on a VCPU. If there is a need for this, we would * need to make this VCPU exit and re-evaluate the priorities, potentially * leading to this interrupt getting presented now to the guest (if it has * been masked by the priority mask before). */ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 8); int i; unsigned long flags; for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); if (irq->hw && vgic_irq_is_sgi(irq->intid)) vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 2); u32 value = 0; int i; for (i = 0; i < len * 4; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->config == VGIC_CONFIG_EDGE) value |= (2U << (i * 2)); vgic_put_irq(vcpu->kvm, irq); } return value; } void vgic_mmio_write_config(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 2); int i; unsigned long flags; for (i = 0; i < len * 4; i++) { struct vgic_irq *irq; /* * The configuration cannot be changed for SGIs in general, * for PPIs this is IMPLEMENTATION DEFINED. The arch timer * code relies on PPIs being level triggered, so we also * make them read-only here. */ if (intid + i < VGIC_NR_PRIVATE_IRQS) continue; irq = vgic_get_irq(vcpu->kvm, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i * 2 + 1, &val)) irq->config = VGIC_CONFIG_EDGE; else irq->config = VGIC_CONFIG_LEVEL; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } u32 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid) { int i; u32 val = 0; int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; for (i = 0; i < 32; i++) { struct vgic_irq *irq; if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) continue; irq = vgic_get_vcpu_irq(vcpu, intid + i); if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level) val |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return val; } void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, const u32 val) { int i; int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; unsigned long flags; for (i = 0; i < 32; i++) { struct vgic_irq *irq; bool new_level; if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) continue; irq = vgic_get_vcpu_irq(vcpu, intid + i); /* * Line level is set irrespective of irq type * (level or edge) to avoid dependency that VM should * restore irq config before line level. */ new_level = !!(val & (1U << i)); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->line_level = new_level; if (new_level) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } static int match_region(const void *key, const void *elt) { const unsigned int offset = (unsigned long)key; const struct vgic_register_region *region = elt; if (offset < region->reg_offset) return -1; if (offset >= region->reg_offset + region->len) return 1; return 0; } const struct vgic_register_region * vgic_find_mmio_region(const struct vgic_register_region *regions, int nr_regions, unsigned int offset) { return bsearch((void *)(uintptr_t)offset, regions, nr_regions, sizeof(regions[0]), match_region); } void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_set_vmcr(vcpu, vmcr); else vgic_v3_set_vmcr(vcpu, vmcr); } void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_get_vmcr(vcpu, vmcr); else vgic_v3_get_vmcr(vcpu, vmcr); } /* * kvm_mmio_read_buf() returns a value in a format where it can be converted * to a byte array and be directly observed as the guest wanted it to appear * in memory if it had done the store itself, which is LE for the GIC, as the * guest knows the GIC is always LE. * * We convert this value to the CPUs native format to deal with it as a data * value. */ unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len) { unsigned long data = kvm_mmio_read_buf(val, len); switch (len) { case 1: return data; case 2: return le16_to_cpu(data); case 4: return le32_to_cpu(data); default: return le64_to_cpu(data); } } /* * kvm_mmio_write_buf() expects a value in a format such that if converted to * a byte array it is observed as the guest would see it if it could perform * the load directly. Since the GIC is LE, and the guest knows this, the * guest expects a value in little endian format. * * We convert the data value from the CPUs native format to LE so that the * value is returned in the proper format. */ void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, unsigned long data) { switch (len) { case 1: break; case 2: data = cpu_to_le16(data); break; case 4: data = cpu_to_le32(data); break; default: data = cpu_to_le64(data); } kvm_mmio_write_buf(buf, len, data); } static struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev) { return container_of(dev, struct vgic_io_device, dev); } static bool check_region(const struct kvm *kvm, const struct vgic_register_region *region, gpa_t addr, int len) { int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; switch (len) { case sizeof(u8): flags = VGIC_ACCESS_8bit; break; case sizeof(u32): flags = VGIC_ACCESS_32bit; break; case sizeof(u64): flags = VGIC_ACCESS_64bit; break; default: return false; } if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { if (!region->bits_per_irq) return true; /* Do we access a non-allocated IRQ? */ return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs; } return false; } const struct vgic_register_region * vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, int len) { const struct vgic_register_region *region; region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, addr - iodev->base_addr); if (!region || !check_region(vcpu->kvm, region, addr, len)) return NULL; return region; } static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, u32 *val) { const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); if (!region) { *val = 0; return 0; } r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; if (region->uaccess_read) *val = region->uaccess_read(r_vcpu, addr, sizeof(u32)); else *val = region->read(r_vcpu, addr, sizeof(u32)); return 0; } static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, const u32 *val) { const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); if (!region) return 0; r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; if (region->uaccess_write) return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val); region->write(r_vcpu, addr, sizeof(u32), *val); return 0; } /* * Userland access to VGIC registers. */ int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, bool is_write, int offset, u32 *val) { if (is_write) return vgic_uaccess_write(vcpu, dev, offset, val); else return vgic_uaccess_read(vcpu, dev, offset, val); } static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; unsigned long data = 0; region = vgic_get_mmio_region(vcpu, iodev, addr, len); if (!region) { memset(val, 0, len); return 0; } switch (iodev->iodev_type) { case IODEV_CPUIF: data = region->read(vcpu, addr, len); break; case IODEV_DIST: data = region->read(vcpu, addr, len); break; case IODEV_REDIST: data = region->read(iodev->redist_vcpu, addr, len); break; case IODEV_ITS: data = region->its_read(vcpu->kvm, iodev->its, addr, len); break; } vgic_data_host_to_mmio_bus(val, len, data); return 0; } static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; unsigned long data = vgic_data_mmio_bus_to_host(val, len); region = vgic_get_mmio_region(vcpu, iodev, addr, len); if (!region) return 0; switch (iodev->iodev_type) { case IODEV_CPUIF: region->write(vcpu, addr, len, data); break; case IODEV_DIST: region->write(vcpu, addr, len, data); break; case IODEV_REDIST: region->write(iodev->redist_vcpu, addr, len, data); break; case IODEV_ITS: region->its_write(vcpu->kvm, iodev->its, addr, len, data); break; } return 0; } const struct kvm_io_device_ops kvm_io_gic_ops = { .read = dispatch_mmio_read, .write = dispatch_mmio_write, }; int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type type) { struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; unsigned int len; switch (type) { case VGIC_V2: len = vgic_v2_init_dist_iodev(io_device); break; case VGIC_V3: len = vgic_v3_init_dist_iodev(io_device); break; default: BUG_ON(1); } io_device->base_addr = dist_base_address; io_device->iodev_type = IODEV_DIST; io_device->redist_vcpu = NULL; return kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, len, &io_device->dev); } |
| 270 272 854 855 272 272 273 272 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> * * For policy-specific per-blkcg data: * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it> * Arianna Avanzini <avanzini.arianna@gmail.com> */ #include <linux/ioprio.h> #include <linux/kdev_t.h> #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/ctype.h> #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/part_stat.h> #include "blk.h" #include "blk-cgroup.h" #include "blk-ioprio.h" #include "blk-throttle.h" static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu); /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. * blkcg_pol_register_mutex nests outside of it and synchronizes entire * policy [un]register operations including cgroup file additions / * removals. Putting cgroup file registration outside blkcg_pol_mutex * allows grabbing it from cgroup callbacks. */ static DEFINE_MUTEX(blkcg_pol_register_mutex); static DEFINE_MUTEX(blkcg_pol_mutex); struct blkcg blkcg_root; EXPORT_SYMBOL_GPL(blkcg_root); struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css; EXPORT_SYMBOL_GPL(blkcg_root_css); static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS]; static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */ bool blkcg_debug_stats = false; static DEFINE_RAW_SPINLOCK(blkg_stat_lock); #define BLKG_DESTROY_BATCH_SIZE 64 /* * Lockless lists for tracking IO stats update * * New IO stats are stored in the percpu iostat_cpu within blkcg_gq (blkg). * There are multiple blkg's (one for each block device) attached to each * blkcg. The rstat code keeps track of which cpu has IO stats updated, * but it doesn't know which blkg has the updated stats. If there are many * block devices in a system, the cost of iterating all the blkg's to flush * out the IO stats can be high. To reduce such overhead, a set of percpu * lockless lists (lhead) per blkcg are used to track the set of recently * updated iostat_cpu's since the last flush. An iostat_cpu will be put * onto the lockless list on the update side [blk_cgroup_bio_start()] if * not there yet and then removed when being flushed [blkcg_rstat_flush()]. * References to blkg are gotten and then put back in the process to * protect against blkg removal. * * Return: 0 if successful or -ENOMEM if allocation fails. */ static int init_blkcg_llists(struct blkcg *blkcg) { int cpu; blkcg->lhead = alloc_percpu_gfp(struct llist_head, GFP_KERNEL); if (!blkcg->lhead) return -ENOMEM; for_each_possible_cpu(cpu) init_llist_head(per_cpu_ptr(blkcg->lhead, cpu)); return 0; } /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static bool blkcg_policy_enabled(struct request_queue *q, const struct blkcg_policy *pol) { return pol && test_bit(pol->plid, q->blkcg_pols); } static void blkg_free_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, free_work); struct request_queue *q = blkg->q; int i; /* * pd_free_fn() can also be called from blkcg_deactivate_policy(), * in order to make sure pd_free_fn() is called in order, the deletion * of the list blkg->q_node is delayed to here from blkg_destroy(), and * blkcg_mutex is used to synchronize blkg_free_workfn() and * blkcg_deactivate_policy(). */ mutex_lock(&q->blkcg_mutex); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); if (blkg->parent) blkg_put(blkg->parent); spin_lock_irq(&q->queue_lock); list_del_init(&blkg->q_node); spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); blk_put_queue(q); free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } /** * blkg_free - free a blkg * @blkg: blkg to free * * Free @blkg which may be partially allocated. */ static void blkg_free(struct blkcg_gq *blkg) { if (!blkg) return; /* * Both ->pd_free_fn() and request queue's release handler may * sleep, so free us by scheduling one work func */ INIT_WORK(&blkg->free_work, blkg_free_workfn); schedule_work(&blkg->free_work); } static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); struct blkcg *blkcg = blkg->blkcg; int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif /* * Flush all the non-empty percpu lockless lists before releasing * us, given these stat belongs to us. * * blkg_stat_lock is for serializing blkg stat update */ for_each_possible_cpu(cpu) __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); blkg_free(blkg); } /* * A group is RCU protected, but having an rcu lock does not mean that one * can access all the fields of blkg and assume these are valid. For * example, don't try to follow throtl_data and request queue links. * * Having a reference to blkg under an rcu allows accesses to only values * local to groups like group stats and group rate limits. */ static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); call_rcu(&blkg->rcu_head, __blkg_release); } #ifdef CONFIG_BLK_CGROUP_PUNT_BIO static struct workqueue_struct *blkcg_punt_bio_wq; static void blkg_async_bio_workfn(struct work_struct *work) { struct blkcg_gq *blkg = container_of(work, struct blkcg_gq, async_bio_work); struct bio_list bios = BIO_EMPTY_LIST; struct bio *bio; struct blk_plug plug; bool need_plug = false; /* as long as there are pending bios, @blkg can't go away */ spin_lock(&blkg->async_bio_lock); bio_list_merge_init(&bios, &blkg->async_bios); spin_unlock(&blkg->async_bio_lock); /* start plug only when bio_list contains at least 2 bios */ if (bios.head && bios.head->bi_next) { need_plug = true; blk_start_plug(&plug); } while ((bio = bio_list_pop(&bios))) submit_bio(bio); if (need_plug) blk_finish_plug(&plug); } /* * When a shared kthread issues a bio for a cgroup, doing so synchronously can * lead to priority inversions as the kthread can be trapped waiting for that * cgroup. Use this helper instead of submit_bio to punt the actual issuing to * a dedicated per-blkcg work item to avoid such priority inversions. */ void blkcg_punt_bio_submit(struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; if (blkg->parent) { spin_lock(&blkg->async_bio_lock); bio_list_add(&blkg->async_bios, bio); spin_unlock(&blkg->async_bio_lock); queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work); } else { /* never bounce for the root cgroup */ submit_bio(bio); } } EXPORT_SYMBOL_GPL(blkcg_punt_bio_submit); static int __init blkcg_punt_bio_init(void) { blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio", WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND | WQ_SYSFS, 0); if (!blkcg_punt_bio_wq) return -ENOMEM; return 0; } subsys_initcall(blkcg_punt_bio_init); #endif /* CONFIG_BLK_CGROUP_PUNT_BIO */ /** * bio_blkcg_css - return the blkcg CSS associated with a bio * @bio: target bio * * This returns the CSS for the blkcg associated with a bio, or %NULL if not * associated. Callers are expected to either handle %NULL or know association * has been done prior to calling this. */ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { if (!bio || !bio->bi_blkg) return NULL; return &bio->bi_blkg->blkcg->css; } EXPORT_SYMBOL_GPL(bio_blkcg_css); /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg associating @blkcg and @disk. */ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto out_free_blkg; blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); if (!blkg->iostat_cpu) goto out_exit_refcnt; if (!blk_get_queue(disk->queue)) goto out_free_iostat; blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; blkg->iostat.blkg = blkg; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); #endif u64_stats_init(&blkg->iostat.sync); for_each_possible_cpu(cpu) { u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); per_cpu_ptr(blkg->iostat_cpu, cpu)->blkg = blkg; } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ pd = pol->pd_alloc_fn(disk, blkcg, gfp_mask); if (!pd) goto out_free_pds; blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; pd->online = false; } return blkg; out_free_pds: while (--i >= 0) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); blk_put_queue(disk->queue); out_free_iostat: free_percpu(blkg->iostat_cpu); out_exit_refcnt: percpu_ref_exit(&blkg->refcnt); out_free_blkg: kfree(blkg); return NULL; } /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { ret = -ENODEV; goto err_free_blkg; } /* allocate */ if (!new_blkg) { new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; } } blkg = new_blkg; /* link parent */ if (blkcg_parent(blkcg)) { blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; } blkg_get(blkg->parent); } /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_init_fn) pol->pd_init_fn(blkg->pd[i]); } /* insert */ spin_lock(&blkcg->lock); ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i]) { if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[i]); blkg->pd[i]->online = true; } } } blkg->online = true; spin_unlock(&blkcg->lock); if (!ret) return blkg; /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); return ERR_PTR(ret); err_put_css: css_put(&blkcg->css); err_free_blkg: if (new_blkg) blkg_free(new_blkg); return ERR_PTR(ret); } /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @disk: gendisk of interest * * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; WARN_ON_ONCE(!rcu_read_lock_held()); blkg = blkg_lookup(blkcg, q); if (blkg) return blkg; spin_lock_irqsave(&q->queue_lock, flags); blkg = blkg_lookup(blkcg, q); if (blkg) { if (blkcg != &blkcg_root && blkg != rcu_dereference(blkcg->blkg_hint)) rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. Returns the closest * blkg to the intended blkg should blkg_create() fail. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; break; } pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; } if (pos == blkcg) break; } found: spin_unlock_irqrestore(&q->queue_lock, flags); return blkg; } static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; int i; lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* * blkg stays on the queue list until blkg_free_workfn(), see details in * blkg_free_workfn(), hence this function can be called from * blkcg_destroy_blkgs() first and again from blkg_destroy_all() before * blkg_free_workfn(). */ if (hlist_unhashed(&blkg->blkcg_node)) return; for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && blkg->pd[i]->online) { blkg->pd[i]->online = false; if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[i]); } } blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); hlist_del_init_rcu(&blkg->blkcg_node); /* * Both setting lookup hint to and clearing it from @blkg are done * under queue_lock. If it's not pointing to @blkg now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(blkcg->blkg_hint) == blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ percpu_ref_kill(&blkg->refcnt); } static void blkg_destroy_all(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; int count = BLKG_DESTROY_BATCH_SIZE; int i; restart: spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; if (hlist_unhashed(&blkg->blkcg_node)) continue; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); /* * in order to avoid holding the spin lock for too long, release * it when a batch of blkgs are destroyed. */ if (!(--count)) { count = BLKG_DESTROY_BATCH_SIZE; spin_unlock_irq(&q->queue_lock); cond_resched(); goto restart; } } /* * Mark policy deactivated since policy offline has been done, and * the free is scheduled, so future blkcg_deactivate_policy() can * be bypassed */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (pol) __clear_bit(pol->plid, q->blkcg_pols); } q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] = src->bytes[i]; dst->ios[i] = src->ios[i]; } } static void __blkg_clear_stat(struct blkg_iostat_set *bis) { struct blkg_iostat cur = {0}; unsigned long flags; flags = u64_stats_update_begin_irqsave(&bis->sync); blkg_iostat_set(&bis->cur, &cur); blkg_iostat_set(&bis->last, &cur); u64_stats_update_end_irqrestore(&bis->sync, flags); } static void blkg_clear_stat(struct blkcg_gq *blkg) { int cpu; for_each_possible_cpu(cpu) { struct blkg_iostat_set *s = per_cpu_ptr(blkg->iostat_cpu, cpu); __blkg_clear_stat(s); } __blkg_clear_stat(&blkg->iostat); } static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; int i; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); /* * Note that stat reset is racy - it doesn't synchronize against * stat updates. This is a debug feature which shouldn't exist * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { blkg_clear_stat(blkg); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (blkg->pd[i] && pol->pd_reset_stats_fn) pol->pd_reset_stats_fn(blkg->pd[i]); } } spin_unlock_irq(&blkcg->lock); mutex_unlock(&blkcg_pol_mutex); return 0; } const char *blkg_dev_name(struct blkcg_gq *blkg) { if (!blkg->q->disk) return NULL; return bdi_dev_name(blkg->q->disk->bdi); } /** * blkcg_print_blkgs - helper for printing per-blkg data * @sf: seq_file to print to * @blkcg: blkcg of interest * @prfill: fill function to print out a blkg * @pol: policy in question * @data: data to be passed to @prfill * @show_total: to print out sum of prfill return values or not * * This function invokes @prfill on each blkg of @blkcg if pd for the * policy specified by @pol exists. @prfill is invoked with @sf, the * policy data and @data and the matching queue lock held. If @show_total * is %true, the sum of the return values from @prfill is printed with * "Total" label at the end. * * This is to be used to construct print functions for * cftype->read_seq_string method. */ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total) { struct blkcg_gq *blkg; u64 total = 0; rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); if (show_total) seq_printf(sf, "Total %llu\n", (unsigned long long)total); } EXPORT_SYMBOL_GPL(blkcg_print_blkgs); /** * __blkg_prfill_u64 - prfill helper for a single u64 value * @sf: seq_file to print to * @pd: policy private data of interest * @v: value to print * * Print @v to @sf for the device associated with @pd. */ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) { const char *dname = blkg_dev_name(pd->blkg); if (!dname) return 0; seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v); return v; } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); /** * blkg_conf_init - initialize a blkg_conf_ctx * @ctx: blkg_conf_ctx to initialize * @input: input string * * Initialize @ctx which can be used to parse blkg config input string @input. * Once initialized, @ctx can be used with blkg_conf_open_bdev() and * blkg_conf_prep(), and must be cleaned up with blkg_conf_exit(). */ void blkg_conf_init(struct blkg_conf_ctx *ctx, char *input) { *ctx = (struct blkg_conf_ctx){ .input = input }; } EXPORT_SYMBOL_GPL(blkg_conf_init); /** * blkg_conf_open_bdev - parse and open bdev for per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse the device node prefix part, MAJ:MIN, of per-blkg config update from * @ctx->input and get and store the matching bdev in @ctx->bdev. @ctx->body is * set to point past the device node prefix. * * This function may be called multiple times on @ctx and the extra calls become * NOOPs. blkg_conf_prep() implicitly calls this function. Use this function * explicitly if bdev access is needed without resolving the blkcg / policy part * of @ctx->input. Returns -errno on error. */ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx) { char *input = ctx->input; unsigned int major, minor; struct block_device *bdev; int key_len; if (ctx->bdev) return 0; if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2) return -EINVAL; input += key_len; if (!isspace(*input)) return -EINVAL; input = skip_spaces(input); bdev = blkdev_get_no_open(MKDEV(major, minor)); if (!bdev) return -ENODEV; if (bdev_is_partition(bdev)) { blkdev_put_no_open(bdev); return -ENODEV; } mutex_lock(&bdev->bd_queue->rq_qos_mutex); if (!disk_live(bdev->bd_disk)) { blkdev_put_no_open(bdev); mutex_unlock(&bdev->bd_queue->rq_qos_mutex); return -ENODEV; } ctx->body = input; ctx->bdev = bdev; return 0; } /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup * @pol: target policy * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Parse per-blkg config update from @ctx->input and initialize @ctx * accordingly. On success, @ctx->body points to the part of @ctx->input * following MAJ:MIN, @ctx->bdev points to the target block device and * @ctx->blkg to the blkg being configured. * * blkg_conf_open_bdev() may be called on @ctx beforehand. On success, this * function returns with queue lock held and must be followed by * blkg_conf_exit(). */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkg_conf_ctx *ctx) __acquires(&bdev->bd_queue->queue_lock) { struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; ret = blkg_conf_open_bdev(ctx); if (ret) return ret; disk = ctx->bdev->bd_disk; q = disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab * q_usage_counter to prevent concurrent with blkcg_deactivate_policy(). */ ret = blk_queue_enter(q, 0); if (ret) goto fail; spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { ret = -EOPNOTSUPP; goto fail_unlock; } blkg = blkg_lookup(blkcg, q); if (blkg) goto success; /* * Create blkgs walking down from blkcg_root to @blkcg, so that all * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent; struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ spin_unlock_irq(&q->queue_lock); new_blkg = blkg_alloc(pos, disk, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; } if (radix_tree_preload(GFP_KERNEL)) { blkg_free(new_blkg); ret = -ENOMEM; goto fail_exit_queue; } spin_lock_irq(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); ret = -EOPNOTSUPP; goto fail_preloaded; } blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; } } radix_tree_preload_end(); if (pos == blkcg) goto success; } success: blk_queue_exit(q); ctx->blkg = blkg; return 0; fail_preloaded: radix_tree_preload_end(); fail_unlock: spin_unlock_irq(&q->queue_lock); fail_exit_queue: blk_queue_exit(q); fail: /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue * can be bypassing for some time and it's always nice to * avoid busy looping. */ if (ret == -EBUSY) { msleep(10); ret = restart_syscall(); } return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); /** * blkg_conf_exit - clean up per-blkg config update * @ctx: blkg_conf_ctx initialized with blkg_conf_init() * * Clean up after per-blkg config update. This function must be called on all * blkg_conf_ctx's initialized with blkg_conf_init(). */ void blkg_conf_exit(struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) __releases(&ctx->bdev->bd_queue->rq_qos_mutex) { if (ctx->blkg) { spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock); ctx->blkg = NULL; } if (ctx->bdev) { mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex); blkdev_put_no_open(ctx->bdev); ctx->body = NULL; ctx->bdev = NULL; } } EXPORT_SYMBOL_GPL(blkg_conf_exit); static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] += src->bytes[i]; dst->ios[i] += src->ios[i]; } } static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) { int i; for (i = 0; i < BLKG_IOSTAT_NR; i++) { dst->bytes[i] -= src->bytes[i]; dst->ios[i] -= src->ios[i]; } } static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, struct blkg_iostat *last) { struct blkg_iostat delta; unsigned long flags; /* propagate percpu delta to global */ flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&delta, cur); blkg_iostat_sub(&delta, last); blkg_iostat_add(&blkg->iostat.cur, &delta); blkg_iostat_add(last, &delta); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } static void __blkcg_rstat_flush(struct blkcg *blkcg, int cpu) { struct llist_head *lhead = per_cpu_ptr(blkcg->lhead, cpu); struct llist_node *lnode; struct blkg_iostat_set *bisc, *next_bisc; unsigned long flags; rcu_read_lock(); lnode = llist_del_all(lhead); if (!lnode) goto out; /* * For covering concurrent parent blkg update from blkg_release(). * * When flushing from cgroup, cgroup_rstat_lock is always held, so * this lock won't cause contention most of time. */ raw_spin_lock_irqsave(&blkg_stat_lock, flags); /* * Iterate only the iostat_cpu's queued in the lockless list. */ llist_for_each_entry_safe(bisc, next_bisc, lnode, lnode) { struct blkcg_gq *blkg = bisc->blkg; struct blkcg_gq *parent = blkg->parent; struct blkg_iostat cur; unsigned int seq; /* * Order assignment of `next_bisc` from `bisc->lnode.next` in * llist_for_each_entry_safe and clearing `bisc->lqueued` for * avoiding to assign `next_bisc` with new next pointer added * in blk_cgroup_bio_start() in case of re-ordering. * * The pair barrier is implied in llist_add() in blk_cgroup_bio_start(). */ smp_mb(); WRITE_ONCE(bisc->lqueued, false); if (bisc == &blkg->iostat) goto propagate_up; /* propagate up to parent only */ /* fetch the current per-cpu values */ do { seq = u64_stats_fetch_begin(&bisc->sync); blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); blkcg_iostat_update(blkg, &cur, &bisc->last); propagate_up: /* propagate global delta to parent (unless that's root) */ if (parent && parent->parent) { blkcg_iostat_update(parent, &blkg->iostat.cur, &blkg->iostat.last); /* * Queue parent->iostat to its blkcg's lockless * list to propagate up to the grandparent if the * iostat hasn't been queued yet. */ if (!parent->iostat.lqueued) { struct llist_head *plhead; plhead = per_cpu_ptr(parent->blkcg->lhead, cpu); llist_add(&parent->iostat.lnode, plhead); parent->iostat.lqueued = true; } } } raw_spin_unlock_irqrestore(&blkg_stat_lock, flags); out: rcu_read_unlock(); } static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { /* Root-level stats are sourced from system-wide IO stats */ if (cgroup_parent(css->cgroup)) __blkcg_rstat_flush(css_to_blkcg(css), cpu); } /* * We source root cgroup stats from the system-wide stats to avoid * tracking the same information twice and incurring overhead when no * cgroups are defined. For that reason, cgroup_rstat_flush in * blkcg_print_stat does not actually fill out the iostat in the root * cgroup's blkcg_gq. * * However, we would like to re-use the printing code between the root and * non-root cgroups to the extent possible. For that reason, we simulate * flushing the root cgroup's stats by explicitly filling in the iostat * with disk level statistics. */ static void blkcg_fill_root_iostats(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; memset(&tmp, 0, sizeof(tmp)); for_each_possible_cpu(cpu) { struct disk_stats *cpu_dkstats; cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu); tmp.ios[BLKG_IOSTAT_READ] += cpu_dkstats->ios[STAT_READ]; tmp.ios[BLKG_IOSTAT_WRITE] += cpu_dkstats->ios[STAT_WRITE]; tmp.ios[BLKG_IOSTAT_DISCARD] += cpu_dkstats->ios[STAT_DISCARD]; // convert sectors to bytes tmp.bytes[BLKG_IOSTAT_READ] += cpu_dkstats->sectors[STAT_READ] << 9; tmp.bytes[BLKG_IOSTAT_WRITE] += cpu_dkstats->sectors[STAT_WRITE] << 9; tmp.bytes[BLKG_IOSTAT_DISCARD] += cpu_dkstats->sectors[STAT_DISCARD] << 9; } flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); blkg_iostat_set(&blkg->iostat.cur, &tmp); u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); } class_dev_iter_exit(&iter); } static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s) { struct blkg_iostat_set *bis = &blkg->iostat; u64 rbytes, wbytes, rios, wios, dbytes, dios; const char *dname; unsigned seq; int i; if (!blkg->online) return; dname = blkg_dev_name(blkg); if (!dname) return; seq_printf(s, "%s ", dname); do { seq = u64_stats_fetch_begin(&bis->sync); rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; rios = bis->cur.ios[BLKG_IOSTAT_READ]; wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { seq_printf(s, "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu", rbytes, wbytes, rios, wios, dbytes, dios); } if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) { seq_printf(s, " use_delay=%d delay_nsec=%llu", atomic_read(&blkg->use_delay), atomic64_read(&blkg->delay_nsec)); } for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; if (!blkg->pd[i] || !pol->pd_stat_fn) continue; pol->pd_stat_fn(blkg->pd[i], s); } seq_puts(s, "\n"); } static int blkcg_print_stat(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; if (!seq_css(sf)->parent) blkcg_fill_root_iostats(); else cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { spin_lock_irq(&blkg->q->queue_lock); blkcg_print_one_stat(blkg, sf); spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); return 0; } static struct cftype blkcg_files[] = { { .name = "stat", .seq_show = blkcg_print_stat, }, { } /* terminate */ }; static struct cftype blkcg_legacy_files[] = { { .name = "reset_stats", .write_u64 = blkcg_reset_stats, }, { } /* terminate */ }; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css) { return &css_to_blkcg(css)->cgwb_list; } #endif /* * blkcg destruction is a three-stage process. * * 1. Destruction starts. The blkcg_css_offline() callback is invoked * which offlines writeback. Here we tie the next stage of blkg destruction * to the completion of writeback associated with the blkcg. This lets us * avoid punting potentially large amounts of outstanding writeback to root * while maintaining any ongoing policies. The next stage is triggered when * the nr_cgwbs count goes to zero. * * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called * and handles the destruction of blkgs. Here the css reference held by * the blkg is put back eventually allowing blkcg_css_free() to be called. * This work may occur in cgwb_release_workfn() on the cgwb_release * workqueue. Any submitted ios that fail to get the blkg ref will be * punted to the root_blkg. * * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. * This finally frees the blkcg. */ /** * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. * Destroying the blkgs releases the reference held on the blkcg's css allowing * blkcg_css_free to eventually be called. * * This is the blkcg counterpart of ioc_release_fn(). */ static void blkcg_destroy_blkgs(struct blkcg *blkcg) { might_sleep(); spin_lock_irq(&blkcg->lock); while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (need_resched() || !spin_trylock(&q->queue_lock)) { /* * Given that the system can accumulate a huge number * of blkgs in pathological cases, check to see if we * need to rescheduling to avoid softlockup. */ spin_unlock_irq(&blkcg->lock); cond_resched(); spin_lock_irq(&blkcg->lock); continue; } blkg_destroy(blkg); spin_unlock(&q->queue_lock); } spin_unlock_irq(&blkcg->lock); } /** * blkcg_pin_online - pin online state * @blkcg_css: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css) { refcount_inc(&css_to_blkcg(blkcg_css)->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg_css: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) { struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { struct blkcg *parent; if (!refcount_dec_and_test(&blkcg->online_pin)) break; parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); blkcg = parent; } while (blkcg); } /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * * This function is called when @css is about to go away. Here the cgwbs are * offlined first and only once writeback associated with the blkcg has * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(css); /* put the base online pin allowing step 2 to be triggered */ blkcg_unpin_online(css); } static void blkcg_css_free(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); int i; mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); for (i = 0; i < BLKCG_MAX_POLS; i++) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); mutex_unlock(&blkcg_pol_mutex); free_percpu(blkcg->lhead); kfree(blkcg); } static struct cgroup_subsys_state * blkcg_css_alloc(struct cgroup_subsys_state *parent_css) { struct blkcg *blkcg; int i; mutex_lock(&blkcg_pol_mutex); if (!parent_css) { blkcg = &blkcg_root; } else { blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL); if (!blkcg) goto unlock; } if (init_blkcg_llists(blkcg)) goto free_blkcg; for (i = 0; i < BLKCG_MAX_POLS ; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkcg_policy_data *cpd; /* * If the policy hasn't been attached yet, wait for it * to be attached before doing anything else. Otherwise, * check if the policy requires any specific per-cgroup * data: if it does, allocate and initialize it. */ if (!pol || !pol->cpd_alloc_fn) continue; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto free_pd_blkcg; blkcg->cpd[i] = cpd; cpd->blkcg = blkcg; cpd->plid = i; } spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); mutex_unlock(&blkcg_pol_mutex); return &blkcg->css; free_pd_blkcg: for (i--; i >= 0; i--) if (blkcg->cpd[i]) blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]); free_percpu(blkcg->lhead); free_blkcg: if (blkcg != &blkcg_root) kfree(blkcg); unlock: mutex_unlock(&blkcg_pol_mutex); return ERR_PTR(-ENOMEM); } static int blkcg_css_online(struct cgroup_subsys_state *css) { struct blkcg *parent = blkcg_parent(css_to_blkcg(css)); /* * blkcg_pin_online() is used to delay blkcg offline so that blkgs * don't go offline while cgwbs are still active on them. Pin the * parent so that offline always happens towards the root. */ if (parent) blkcg_pin_online(&parent->css); return 0; } void blkg_init_queue(struct request_queue *q) { INIT_LIST_HEAD(&q->blkg_list); mutex_init(&q->blkcg_mutex); } int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; preloaded = !radix_tree_preload(GFP_KERNEL); /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return 0; err_unlock: spin_unlock_irq(&q->queue_lock); if (preloaded) radix_tree_preload_end(); return PTR_ERR(blkg); } void blkcg_exit_disk(struct gendisk *disk) { blkg_destroy_all(disk); blk_throtl_exit(disk); } static void blkcg_exit(struct task_struct *tsk) { if (tsk->throttle_disk) put_disk(tsk->throttle_disk); tsk->throttle_disk = NULL; } struct cgroup_subsys io_cgrp_subsys = { .css_alloc = blkcg_css_alloc, .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .css_rstat_flush = blkcg_rstat_flush, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, .legacy_name = "blkio", .exit = blkcg_exit, #ifdef CONFIG_MEMCG /* * This ensures that, if available, memcg is automatically enabled * together on the default hierarchy so that the owner cgroup can * be retrieved from writeback pages. */ .depends_on = 1 << memory_cgrp_id, #endif }; EXPORT_SYMBOL_GPL(io_cgrp_subsys); /** * blkcg_activate_policy - activate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to activate * * Activate @pol on @disk. Requires %GFP_KERNEL context. @disk goes through * bypass mode to populate its blkgs with policy_data for @pol. * * Activation happens with @disk bypassed, so nobody would be accessing blkgs * from IO path. Update of each blkg is protected by both queue and blkcg * locks so that holding either lock and testing blkcg_policy_enabled() is * always enough for dereferencing policy data. * * The caller is responsible for synchronizing [de]activations and policy * [un]registerations. Returns 0 on success, -errno on failure. */ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; unsigned int memflags; int ret; if (blkcg_policy_enabled(q, pol)) return 0; /* * Policy is allowed to be registered without pd_alloc_fn/pd_free_fn, * for example, ioprio. Such policy will work on blkcg level, not disk * level, and don't need to be activated. */ if (WARN_ON_ONCE(!pol->pd_alloc_fn || !pol->pd_free_fn)) return -EINVAL; if (queue_is_mq(q)) memflags = blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); /* blkg_list is pushed at the head, reverse walk to initialize parents first */ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; if (blkg->pd[pol->plid]) continue; /* If prealloc matches, use it; otherwise try GFP_NOWAIT */ if (blkg == pinned_blkg) { pd = pd_prealloc; pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_NOWAIT | __GFP_NOWARN); } if (!pd) { /* * GFP_NOWAIT failed. Free the existing one and * prealloc for @blkg w/ GFP_KERNEL. */ if (pinned_blkg) blkg_put(pinned_blkg); blkg_get(blkg); pinned_blkg = blkg; spin_unlock_irq(&q->queue_lock); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); pd_prealloc = pol->pd_alloc_fn(disk, blkg->blkcg, GFP_KERNEL); if (pd_prealloc) goto retry; else goto enomem; } spin_lock(&blkg->blkcg->lock); pd->blkg = blkg; pd->plid = pol->plid; blkg->pd[pol->plid] = pd; if (pol->pd_init_fn) pol->pd_init_fn(pd); if (pol->pd_online_fn) pol->pd_online_fn(pd); pd->online = true; spin_unlock(&blkg->blkcg->lock); } __set_bit(pol->plid, q->blkcg_pols); ret = 0; spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) blk_mq_unfreeze_queue(q, memflags); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); return ret; enomem: /* alloc failed, take down everything */ spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; struct blkg_policy_data *pd; spin_lock(&blkcg->lock); pd = blkg->pd[pol->plid]; if (pd) { if (pd->online && pol->pd_offline_fn) pol->pd_offline_fn(pd); pd->online = false; pol->pd_free_fn(pd); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); ret = -ENOMEM; goto out; } EXPORT_SYMBOL_GPL(blkcg_activate_policy); /** * blkcg_deactivate_policy - deactivate a blkcg policy on a gendisk * @disk: gendisk of interest * @pol: blkcg policy to deactivate * * Deactivate @pol on @disk. Follows the same synchronization rules as * blkcg_activate_policy(). */ void blkcg_deactivate_policy(struct gendisk *disk, const struct blkcg_policy *pol) { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned int memflags; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) memflags = blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } spin_unlock(&blkcg->lock); } spin_unlock_irq(&q->queue_lock); mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) blk_mq_unfreeze_queue(q, memflags); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); static void blkcg_free_all_cpd(struct blkcg_policy *pol) { struct blkcg *blkcg; list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); blkcg->cpd[pol->plid] = NULL; } } } /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register * * Register @pol with blkcg core. Might sleep and @pol may be modified on * successful registration. Returns 0 on success and -errno on failure. */ int blkcg_policy_register(struct blkcg_policy *pol) { struct blkcg *blkcg; int i, ret; mutex_lock(&blkcg_pol_register_mutex); mutex_lock(&blkcg_pol_mutex); /* find an empty slot */ ret = -ENOSPC; for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; if (i >= BLKCG_MAX_POLS) { pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; } /* * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy * without pd_alloc_fn/pd_free_fn can't be activated. */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || (!pol->pd_alloc_fn ^ !pol->pd_free_fn)) goto err_unlock; /* register @pol */ pol->plid = i; blkcg_policy[pol->plid] = pol; /* allocate and install cpd's */ if (pol->cpd_alloc_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { struct blkcg_policy_data *cpd; cpd = pol->cpd_alloc_fn(GFP_KERNEL); if (!cpd) goto err_free_cpds; blkcg->cpd[pol->plid] = cpd; cpd->blkcg = blkcg; cpd->plid = pol->plid; } } mutex_unlock(&blkcg_pol_mutex); /* everything is in place, add intf files for the new policy */ if (pol->dfl_cftypes) WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys, pol->dfl_cftypes)); if (pol->legacy_cftypes) WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys, pol->legacy_cftypes)); mutex_unlock(&blkcg_pol_register_mutex); return 0; err_free_cpds: if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); mutex_unlock(&blkcg_pol_register_mutex); return ret; } EXPORT_SYMBOL_GPL(blkcg_policy_register); /** * blkcg_policy_unregister - unregister a blkcg policy * @pol: blkcg policy to unregister * * Undo blkcg_policy_register(@pol). Might sleep. */ void blkcg_policy_unregister(struct blkcg_policy *pol) { mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) goto out_unlock; /* kill the intf files first */ if (pol->dfl_cftypes) cgroup_rm_cftypes(pol->dfl_cftypes); if (pol->legacy_cftypes) cgroup_rm_cftypes(pol->legacy_cftypes); /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); if (pol->cpd_free_fn) blkcg_free_all_cpd(pol); blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); out_unlock: mutex_unlock(&blkcg_pol_register_mutex); } EXPORT_SYMBOL_GPL(blkcg_policy_unregister); /* * Scale the accumulated delay based on how long it has been since we updated * the delay. We only call this when we are adding delay, in case it's been a * while since we added delay, and when we are checking to see if we need to * delay a task, to account for any delays that may have occurred. */ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) { u64 old = atomic64_read(&blkg->delay_start); /* negative use_delay means no scaling, see blkcg_set_delay() */ if (atomic_read(&blkg->use_delay) < 0) return; /* * We only want to scale down every second. The idea here is that we * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain * time window. We only want to throttle tasks for recent delay that * has occurred, in 1 second time windows since that's the maximum * things can be throttled. We save the current delay window in * blkg->last_delay so we know what amount is still left to be charged * to the blkg from this point onward. blkg->last_use keeps track of * the use_delay counter. The idea is if we're unthrottling the blkg we * are ok with whatever is happening now, and we can take away more of * the accumulated delay as we've already throttled enough that * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); /* * We've been unthrottled, subtract a larger chunk of our * accumulated delay. */ if (cur_use < blkg->last_use) sub = max_t(u64, sub, blkg->last_delay >> 1); /* * This shouldn't happen, but handle it anyway. Our delay_nsec * should only ever be growing except here where we subtract out * min(last_delay, 1 second), but lord knows bugs happen and I'd * rather not end up with negative numbers. */ if (unlikely(cur < sub)) { atomic64_set(&blkg->delay_nsec, 0); blkg->last_delay = 0; } else { atomic64_sub(sub, &blkg->delay_nsec); blkg->last_delay = cur - sub; } blkg->last_use = cur_use; } } /* * This is called when we want to actually walk up the hierarchy and check to * see if we need to throttle, and then actually throttle if there is some * accumulated delay. This should only be called upon return to user space so * we're not holding some lock that would induce a priority inversion. */ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay) { unsigned long pflags; bool clamp; u64 now = blk_time_get_ns(); u64 exp; u64 delay_nsec = 0; int tok; while (blkg->parent) { int use_delay = atomic_read(&blkg->use_delay); if (use_delay) { u64 this_delay; blkcg_scale_delay(blkg, now); this_delay = atomic64_read(&blkg->delay_nsec); if (this_delay > delay_nsec) { delay_nsec = this_delay; clamp = use_delay > 0; } } blkg = blkg->parent; } if (!delay_nsec) return; /* * Let's not sleep for all eternity if we've amassed a huge delay. * Swapping or metadata IO can accumulate 10's of seconds worth of * delay, and we want userspace to be able to do _something_ so cap the * delays at 0.25s. If there's 10's of seconds worth of delay then the * tasks will be delayed for 0.25 second for every syscall. If * blkcg_set_delay() was used as indicated by negative use_delay, the * caller is responsible for regulating the range. */ if (clamp) delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC); if (use_memdelay) psi_memstall_enter(&pflags); exp = ktime_add_ns(now, delay_nsec); tok = io_schedule_prepare(); do { __set_current_state(TASK_KILLABLE); if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS)) break; } while (!fatal_signal_pending(current)); io_schedule_finish(tok); if (use_memdelay) psi_memstall_leave(&pflags); } /** * blkcg_maybe_throttle_current - throttle the current task if it has been marked * * This is only called if we've been marked with set_notify_resume(). Obviously * we can be set_notify_resume() for reasons other than blkcg throttling, so we * check to see if current->throttle_disk is set and if not this doesn't do * anything. This should only ever be called by the resume code, it's not meant * to be called by people willy-nilly as it will actually do the work to * throttle the task if it is setup for throttling. */ void blkcg_maybe_throttle_current(void) { struct gendisk *disk = current->throttle_disk; struct blkcg *blkcg; struct blkcg_gq *blkg; bool use_memdelay = current->use_memdelay; if (!disk) return; current->throttle_disk = NULL; current->use_memdelay = false; rcu_read_lock(); blkcg = css_to_blkcg(blkcg_css()); if (!blkcg) goto out; blkg = blkg_lookup(blkcg, disk->queue); if (!blkg) goto out; if (!blkg_tryget(blkg)) goto out; rcu_read_unlock(); blkcg_maybe_throttle_blkg(blkg, use_memdelay); blkg_put(blkg); put_disk(disk); return; out: rcu_read_unlock(); } /** * blkcg_schedule_throttle - this task needs to check for throttling * @disk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * * We will only schedule once per syscall. You can call this over and over * again and it will only do the check once upon return to user space, and only * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { if (unlikely(current->flags & PF_KTHREAD)) return; if (current->throttle_disk != disk) { if (test_bit(GD_DEAD, &disk->state)) return; get_device(disk_to_dev(disk)); if (current->throttle_disk) put_disk(current->throttle_disk); current->throttle_disk = disk; } if (use_memdelay) current->use_memdelay = use_memdelay; set_notify_resume(current); } /** * blkcg_add_delay - add delay to this blkg * @blkg: blkg of interest * @now: the current time in nanoseconds * @delta: how many nanoseconds of delay to add * * Charge @delta to the blkg's current delay accumulation. This is used to * throttle tasks if an IO controller thinks we need more throttling. */ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; blkcg_scale_delay(blkg, now); atomic64_add(delta, &blkg->delay_nsec); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @bio: target bio * @css: target css * * As the failure mode here is to walk up the blkg tree, this ensure that the * blkg->parent pointers are always valid. This returns the blkg that it ended * up taking a reference on or %NULL if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct cgroup_subsys_state *css) { struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; break; } blkg = blkg->parent; } rcu_read_unlock(); return ret_blkg; } /** * bio_associate_blkg_from_css - associate a bio with a specified css * @bio: target bio * @css: target css * * Associate @bio with the blkg found by combining the css's blkg and the * request_queue of the @bio. An association failure is handled by walking up * the blkg tree. Therefore, the blkg associated can be anything between @blkg * and q->root_blkg. This situation only happens when a cgroup is dying and * then the remaining bios will spill to the closest alive blkg. * * A reference will be taken on the blkg and will be released when @bio is * freed. */ void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { if (bio->bi_blkg) blkg_put(bio->bi_blkg); if (css && css->parent) { bio->bi_blkg = blkg_tryget_closest(bio, css); } else { blkg_get(bdev_get_queue(bio->bi_bdev)->root_blkg); bio->bi_blkg = bdev_get_queue(bio->bi_bdev)->root_blkg; } } EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); /** * bio_associate_blkg - associate a bio with a blkg * @bio: target bio * * Associate @bio with the blkg found from the bio's css and request_queue. * If one is not found, bio_lookup_blkg() creates the blkg. If a blkg is * already associated, the css is reused and association redone as the * request_queue may have changed. */ void bio_associate_blkg(struct bio *bio) { struct cgroup_subsys_state *css; if (blk_op_is_passthrough(bio->bi_opf)) return; rcu_read_lock(); if (bio->bi_blkg) css = bio_blkcg_css(bio); else css = blkcg_css(); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_associate_blkg); /** * bio_clone_blkg_association - clone blkg association from src to dst bio * @dst: destination bio * @src: source bio */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { if (src->bi_blkg) bio_associate_blkg_from_css(dst, bio_blkcg_css(src)); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); static int blk_cgroup_io_type(struct bio *bio) { if (op_is_discard(bio->bi_opf)) return BLKG_IOSTAT_DISCARD; if (op_is_write(bio->bi_opf)) return BLKG_IOSTAT_WRITE; return BLKG_IOSTAT_READ; } void blk_cgroup_bio_start(struct bio *bio) { struct blkcg *blkcg = bio->bi_blkg->blkcg; int rwd = blk_cgroup_io_type(bio), cpu; struct blkg_iostat_set *bis; unsigned long flags; if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) return; /* Root-level stats are sourced from system-wide IO stats */ if (!cgroup_parent(blkcg->css.cgroup)) return; cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); /* * If the bio is flagged with BIO_CGROUP_ACCT it means this is a split * bio and we would have already accounted for the size of the bio. */ if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { bio_set_flag(bio, BIO_CGROUP_ACCT); bis->cur.bytes[rwd] += bio->bi_iter.bi_size; } bis->cur.ios[rwd]++; /* * If the iostat_cpu isn't in a lockless list, put it into the * list to indicate that a stat update is pending. */ if (!READ_ONCE(bis->lqueued)) { struct llist_head *lhead = this_cpu_ptr(blkcg->lhead); llist_add(&bis->lnode, lhead); WRITE_ONCE(bis->lqueued, true); } u64_stats_update_end_irqrestore(&bis->sync, flags); cgroup_rstat_updated(blkcg->css.cgroup, cpu); put_cpu(); } bool blk_cgroup_congested(void) { struct blkcg *blkcg; bool ret = false; rcu_read_lock(); for (blkcg = css_to_blkcg(blkcg_css()); blkcg; blkcg = blkcg_parent(blkcg)) { if (atomic_read(&blkcg->congestion_count)) { ret = true; break; } } rcu_read_unlock(); return ret; } module_param(blkcg_debug_stats, bool, 0644); MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ #define _DEVICE_H_ #include <linux/dev_printk.h> #include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> struct device; struct device_private; struct device_driver; struct driver_private; struct module; struct class; struct subsys_private; struct device_node; struct fwnode_handle; struct iommu_group; struct dev_pin_info; struct dev_iommu; struct msi_device_data; /** * struct subsys_interface - interfaces to device functions * @name: name of the device function * @subsys: subsystem of the devices to attach to * @node: the list of functions registered at the subsystem * @add_dev: device hookup to device function handler * @remove_dev: device hookup to device function handler * * Simple interfaces attached to a subsystem. Multiple interfaces can * attach to a subsystem and its devices. Unlike drivers, they do not * exclusively claim or control devices. Interfaces usually represent * a specific functionality of a subsystem/class of devices. */ struct subsys_interface { const char *name; const struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(const struct bus_type *subsys, const struct attribute_group **groups); int subsys_virtual_register(const struct bus_type *subsys, const struct attribute_group **groups); /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types * like "partitions" and "disks", "mouse" and "event". * This identifies the device type and carries type-specific * information, equivalent to the kobj_type of a kobject. * If "name" is specified, the uevent will contain it in * the DEVTYPE variable. */ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; }; /** * struct device_attribute - Interface for exporting device attributes. * @attr: sysfs attribute definition. * @show: Show handler. * @store: Store handler. */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); }; /** * struct dev_ext_attribute - Exported device attribute with extra context. * @attr: Exported device attribute. * @var: Pointer to context. */ struct dev_ext_attribute { struct device_attribute attr; void *var; }; ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_string(struct device *dev, struct device_attribute *attr, char *buf); /** * DEVICE_ATTR - Define a device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Convenience macro for defining a struct device_attribute. * * For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to: * * .. code-block:: c * * struct device_attribute dev_attr_foo = { * .attr = { .name = "foo", .mode = 0644 }, * .show = foo_show, * .store = foo_store, * }; */ #define DEVICE_ATTR(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) /** * DEVICE_ATTR_PREALLOC - Define a preallocated device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode. */ #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_PREALLOC(_name, _mode, _show, _store) /** * DEVICE_ATTR_RW - Define a read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show, * and @_store is <_name>_store. */ #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) /** * DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RW(), but @_mode is 0600. */ #define DEVICE_ATTR_ADMIN_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) /** * DEVICE_ATTR_RO - Define a readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show. */ #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) /** * DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RO(), but @_mode is 0400. */ #define DEVICE_ATTR_ADMIN_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) /** * DEVICE_ATTR_WO - Define an admin-only writable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store. */ #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) /** * DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of unsigned long. * * Like DEVICE_ATTR(), but @_show and @_store are automatically provided * such that reads and writes to the attribute from userspace affect @_var. */ #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } /** * DEVICE_INT_ATTR - Define a device attribute backed by an int. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of int. * * Like DEVICE_ULONG_ATTR(), but @_var is an int. */ #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } /** * DEVICE_BOOL_ATTR - Define a device attribute backed by a bool. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of bool. * * Like DEVICE_ULONG_ATTR(), but @_var is a bool. */ #define DEVICE_BOOL_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } /** * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of string. * * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the * string allocation is unknown, the attribute must be read-only. */ #define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) int device_create_file(struct device *device, const struct device_attribute *entry); void device_remove_file(struct device *dev, const struct device_attribute *attr); bool device_remove_file_self(struct device *dev, const struct device_attribute *attr); int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); /* device resource management */ typedef void (*dr_release_t)(struct device *dev, void *res); typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data); void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) __malloc; #define devres_alloc(release, size, gfp) \ __devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release) #define devres_alloc_node(release, size, gfp, nid) \ __devres_alloc_node(release, size, gfp, nid, #release) void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data); void devres_free(void *res); void devres_add(struct device *dev, void *res); void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data); void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); /* devres group */ void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp); void devres_close_group(struct device *dev, void *id); void devres_remove_group(struct device *dev, void *id); int devres_release_group(struct device *dev, void *id); /* managed devm_k.alloc/kfree for device drivers */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __alloc_size(2); void *devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp) __must_check __realloc_size(3); __printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) __malloc; __printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) __malloc; static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp) { return devm_kmalloc(dev, size, gfp | __GFP_ZERO); } static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return devm_kmalloc(dev, bytes, flags); } static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags) { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } static inline __realloc_size(3, 4) void * __must_check devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return devm_krealloc(dev, p, bytes, flags); } void devm_kfree(struct device *dev, const void *p); char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp); void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp) __realloc_size(3); unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order); void devm_free_pages(struct device *dev, unsigned long addr); #ifdef CONFIG_HAS_IOMEM void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size); #else static inline void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res) { return ERR_PTR(-EINVAL); } static inline void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, resource_size_t *size) { return ERR_PTR(-EINVAL); } #endif /* allows to add/remove a custom action to devres stack */ int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data); /** * devm_remove_action() - removes previously added custom action * @dev: Device that owns the action * @action: Function implementing the action * @data: Pointer to data passed to @action implementation * * Removes instance of @action previously added by devm_add_action(). * Both action and data should match one of the existing entries. */ static inline void devm_remove_action(struct device *dev, void (*action)(void *), void *data) { WARN_ON(devm_remove_action_nowarn(dev, action, data)); } void devm_release_action(struct device *dev, void (*action)(void *), void *data); int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); #define devm_add_action(dev, action, data) \ __devm_add_action(dev, action, data, #action) static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data, const char *name) { int ret; ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } #define devm_add_action_or_reset(dev, action, data) \ __devm_add_action_or_reset(dev, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); void devm_free_percpu(struct device *dev, void __percpu *pdata); struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about * sg limitations. */ unsigned int max_segment_size; unsigned int min_align_mask; unsigned long segment_boundary_mask; }; /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. */ enum device_link_state { DL_STATE_NONE = -1, DL_STATE_DORMANT = 0, DL_STATE_AVAILABLE, DL_STATE_CONSUMER_PROBE, DL_STATE_ACTIVE, DL_STATE_SUPPLIER_UNBIND, }; /* * Device link flags. * * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) #define DL_FLAG_INFERRED BIT(8) #define DL_FLAG_CYCLE BIT(9) /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. * @DL_DEV_PROBING: A driver is probing. * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. * @DL_DEV_UNBINDING: The driver is unbinding from the device. */ enum dl_dev_state { DL_DEV_NO_DRIVER = 0, DL_DEV_PROBING, DL_DEV_DRIVER_BOUND, DL_DEV_UNBINDING, }; /** * enum device_removable - Whether the device is removable. The criteria for a * device to be classified as removable is determined by its subsystem or bus. * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this * device (default). * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. * @DEVICE_FIXED: Device is not removable by the user. * @DEVICE_REMOVABLE: Device is removable by the user. */ enum device_removable { DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ DEVICE_REMOVABLE_UNKNOWN, DEVICE_FIXED, DEVICE_REMOVABLE, }; /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @defer_sync: Hook to global list of devices that have deferred sync_state. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head defer_sync; enum dl_dev_state status; }; /** * struct dev_msi_info - Device data related to MSI * @domain: The MSI interrupt domain associated to the device * @data: Pointer to MSI device data */ struct dev_msi_info { #ifdef CONFIG_GENERIC_MSI_IRQ struct irq_domain *domain; struct msi_device_data *data; #endif }; /** * enum device_physical_location_panel - Describes which panel surface of the * system's housing the device connection point resides on. * @DEVICE_PANEL_TOP: Device connection point is on the top panel. * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. * @DEVICE_PANEL_BACK: Device connection point is on the back panel. * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. */ enum device_physical_location_panel { DEVICE_PANEL_TOP, DEVICE_PANEL_BOTTOM, DEVICE_PANEL_LEFT, DEVICE_PANEL_RIGHT, DEVICE_PANEL_FRONT, DEVICE_PANEL_BACK, DEVICE_PANEL_UNKNOWN, }; /** * enum device_physical_location_vertical_position - Describes vertical * position of the device connection point on the panel surface. * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. */ enum device_physical_location_vertical_position { DEVICE_VERT_POS_UPPER, DEVICE_VERT_POS_CENTER, DEVICE_VERT_POS_LOWER, }; /** * enum device_physical_location_horizontal_position - Describes horizontal * position of the device connection point on the panel surface. * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. */ enum device_physical_location_horizontal_position { DEVICE_HORI_POS_LEFT, DEVICE_HORI_POS_CENTER, DEVICE_HORI_POS_RIGHT, }; /** * struct device_physical_location - Device data related to physical location * of the device connection point. * @panel: Panel surface of the system's housing that the device connection * point resides on. * @vertical_position: Vertical position of the device connection point within * the panel. * @horizontal_position: Horizontal position of the device connection point * within the panel. * @dock: Set if the device connection point resides in a docking station or * port replicator. * @lid: Set if this device connection point resides on the lid of laptop * system. */ struct device_physical_location { enum device_physical_location_panel panel; enum device_physical_location_vertical_position vertical_position; enum device_physical_location_horizontal_position horizontal_position; bool dock; bool lid; }; /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host * controller. If parent is NULL, the device, is a top-level device, * which is not usually what you want. * @p: Holds the private data of the driver core portions of the device. * See the comment of the struct device_private for detail. * @kobj: A top-level, abstract class from which other classes are derived. * @init_name: Initial name of the device. * @type: The type of device. * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. * Example: For devices on custom boards, as typical of embedded * and SOC based hardware, Linux often uses platform_data to point * to board-specific structures describing devices and how they * are wired. That can include what ports are available, chip * variants, which GPIO pins act in what additional roles, and so * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations * @dma_io_tlb_mem: Software IO TLB allocator. Not for driver use. * @dma_io_tlb_pools: List of transient swiotlb memory pools. * @dma_io_tlb_lock: Protects changes to the list of active pools. * @dma_uses_io_tlb: %true if device has used the software IO TLB. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. * @devt: For creating the sysfs "dev". * @id: device instance * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. * @class: The class of the device. * @groups: Optional attribute groups. * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data * @physical_location: Describes physical location of the device connection * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. * @state_synced: The hardware state of this device has been synced to match * the software state of this device by calling the driver/bus * sync_state() callback. * @can_match: The device has matched with a driver at least once or it is in * a bus (like AMBA) which can't check for matching drivers until * other devices probe successfully. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * @dma_iommu: Device is using default IOMMU implementation for DMA and * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information * that the device model core needs to model the system. Most subsystems, * however, track additional information about the devices they host. As a * result, it is rare for devices to be represented by bare device structures; * instead, that structure, like kobject structures, is usually embedded within * a higher-level representation of the device. */ struct device { struct kobject kobj; struct device *parent; struct device_private *p; const char *init_name; /* initial name of the device */ const struct device_type *type; const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_ENERGY_MODEL struct em_perf_domain *em_pd; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif struct dev_msi_info msi; #ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ #ifdef CONFIG_DMA_DECLARE_COHERENT struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #endif #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif #ifdef CONFIG_SWIOTLB struct io_tlb_mem *dma_io_tlb_mem; #endif #ifdef CONFIG_SWIOTLB_DYNAMIC struct list_head dma_io_tlb_pools; spinlock_t dma_io_tlb_lock; bool dma_uses_io_tlb; #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct dev_iommu *iommu; struct device_physical_location *physical_location; enum device_removable removable; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; bool state_synced:1; bool can_match:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif #ifdef CONFIG_DMA_NEED_SYNC bool dma_skip_sync:1; #endif #ifdef CONFIG_IOMMU_DMA bool dma_iommu:1; #endif }; /** * struct device_link - Device link representation. * @supplier: The device on the supplier end of the link. * @s_node: Hook to the supplier device's list of links to consumers. * @consumer: The device on the consumer end of the link. * @c_node: Hook to the consumer device's list of links to suppliers. * @link_dev: device used to expose link details in sysfs * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { struct device *supplier; struct list_head s_node; struct device *consumer; struct list_head c_node; struct device link_dev; enum device_link_state status; u32 flags; refcount_t rpm_active; struct kref kref; struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU * @dev: Device to perform the check on */ static inline bool device_iommu_mapped(struct device *dev) { return (dev->iommu_group != NULL); } /* Get the wakeup routines, which depend on struct device */ #include <linux/pm_wakeup.h> /** * dev_name - Return a device's name. * @dev: Device with name to get. * Return: The kobject name of the device, or its initial name if unavailable. */ static inline const char *dev_name(const struct device *dev) { /* Use the init name until the kobject becomes available */ if (dev->init_name) return dev->init_name; return kobject_name(&dev->kobj); } /** * dev_bus_name - Return a device's bus/class name, if at all possible * @dev: struct device to get the bus/class name of * * Will return the name of the bus/class the device is attached to. If it is * not attached to a bus/class, an empty string will be returned. */ static inline const char *dev_bus_name(const struct device *dev) { return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); } __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { return dev->numa_node; } static inline void set_dev_node(struct device *dev, int node) { dev->numa_node = node; } #else static inline int dev_to_node(struct device *dev) { return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { } #endif static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; #endif } static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; } static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } static inline struct pm_subsys_data *dev_to_psd(struct device *dev) { return dev ? dev->power.subsys_data : NULL; } static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; } static inline void dev_set_uevent_suppress(struct device *dev, int val) { dev->kobj.uevent_suppress = val; } static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; } static inline void device_enable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = false; } static inline bool device_async_suspend_enabled(struct device *dev) { return !!dev->power.async_suspend; } static inline bool device_pm_not_required(struct device *dev) { return dev->power.no_pm; } static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; } static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.syscore = val; #endif } static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) { dev->power.driver_flags = flags; } static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) { return !!(dev->power.driver_flags & flags); } static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); } static inline int device_lock_interruptible(struct device *dev) { return mutex_lock_interruptible(&dev->mutex); } static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { mutex_unlock(&dev->mutex); } DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T)) static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); } static inline bool dev_has_sync_state(struct device *dev) { if (!dev) return false; if (dev->driver && dev->driver->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline void dev_set_removable(struct device *dev, enum device_removable removable) { dev->removable = removable; } static inline bool dev_is_removable(struct device *dev) { return dev->removable == DEVICE_REMOVABLE; } static inline bool dev_removable_is_valid(struct device *dev) { return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; } /* * High level routines for use by the bus drivers */ int __must_check device_register(struct device *dev); void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) int device_for_each_child(struct device *parent, void *data, device_iter_t fn); int device_for_each_child_reverse(struct device *parent, void *data, device_iter_t fn); int device_for_each_child_reverse_from(struct device *parent, struct device *from, void *data, device_iter_t fn); struct device *device_find_child(struct device *parent, const void *data, device_match_t match); /** * device_find_child_by_name - device iterator for locating a child device. * @parent: parent struct device * @name: name of the child device * * This is similar to the device_find_child() function above, but it * returns a reference to a device that has the name @name. * * NOTE: you will need to drop the reference with put_device() after use. */ static inline struct device *device_find_child_by_name(struct device *parent, const char *name) { return device_find_child(parent, name, device_match_name); } /** * device_find_any_child - device iterator for locating a child device, if any. * @parent: parent struct device * * This is similar to the device_find_child() function above, but it * returns a reference to a child device, if any. * * NOTE: you will need to drop the reference with put_device() after use. */ static inline struct device *device_find_any_child(struct device *parent) { return device_find_child(parent, NULL, device_match_any); } int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } #define __device_lock_set_class(dev, name, key) \ do { \ struct device *__d2 __maybe_unused = dev; \ lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ } while (0) /** * device_lock_set_class - Specify a temporary lock class while a device * is attached to a driver * @dev: device to modify * @key: lock class key data * * This must be called with the device_lock() already held, for example * from driver ->probe(). Take care to only override the default * lockdep_no_validate class. */ #ifdef CONFIG_LOCKDEP #define device_lock_set_class(dev, key) \ do { \ struct device *__d = dev; \ dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ &__lockdep_no_validate__), \ "overriding existing custom lock class\n"); \ __device_lock_set_class(__d, #key, key); \ } while (0) #else #define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) #endif /** * device_lock_reset_class - Return a device to the default lockdep novalidate state * @dev: device to modify * * This must be called with the device_lock() already held, for example * from driver ->remove(). */ #define device_lock_reset_class(dev) \ do { \ struct device *__d __maybe_unused = dev; \ lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ _THIS_IP_); \ } while (0) void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); static inline struct device_node *dev_of_node(struct device *dev) { if (!IS_ENABLED(CONFIG_OF) || !dev) return NULL; return dev->of_node; } static inline int dev_num_vf(struct device *dev) { if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev); return 0; } /* * Root device objects for grouping under /sys/devices */ struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { return dev->platform_data; } /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_add_groups(dev, groups); } static inline void device_remove_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* * get_device - atomically increment the reference count for the device. * */ struct device *get_device(struct device *dev); void put_device(struct device *dev); DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") #endif /* _DEVICE_H_ */ |
| 979 983 983 980 983 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/common.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/string_helpers.h> #include "common.h" /* String table for operation mode. */ const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = { [TOMOYO_CONFIG_DISABLED] = "disabled", [TOMOYO_CONFIG_LEARNING] = "learning", [TOMOYO_CONFIG_PERMISSIVE] = "permissive", [TOMOYO_CONFIG_ENFORCING] = "enforcing" }; /* String table for /sys/kernel/security/tomoyo/profile */ const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = "execute", [TOMOYO_MAC_FILE_OPEN] = "open", [TOMOYO_MAC_FILE_CREATE] = "create", [TOMOYO_MAC_FILE_UNLINK] = "unlink", [TOMOYO_MAC_FILE_GETATTR] = "getattr", [TOMOYO_MAC_FILE_MKDIR] = "mkdir", [TOMOYO_MAC_FILE_RMDIR] = "rmdir", [TOMOYO_MAC_FILE_MKFIFO] = "mkfifo", [TOMOYO_MAC_FILE_MKSOCK] = "mksock", [TOMOYO_MAC_FILE_TRUNCATE] = "truncate", [TOMOYO_MAC_FILE_SYMLINK] = "symlink", [TOMOYO_MAC_FILE_MKBLOCK] = "mkblock", [TOMOYO_MAC_FILE_MKCHAR] = "mkchar", [TOMOYO_MAC_FILE_LINK] = "link", [TOMOYO_MAC_FILE_RENAME] = "rename", [TOMOYO_MAC_FILE_CHMOD] = "chmod", [TOMOYO_MAC_FILE_CHOWN] = "chown", [TOMOYO_MAC_FILE_CHGRP] = "chgrp", [TOMOYO_MAC_FILE_IOCTL] = "ioctl", [TOMOYO_MAC_FILE_CHROOT] = "chroot", [TOMOYO_MAC_FILE_MOUNT] = "mount", [TOMOYO_MAC_FILE_UMOUNT] = "unmount", [TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root", /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = "inet_stream_bind", [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = "inet_stream_listen", [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = "inet_stream_connect", [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = "inet_dgram_bind", [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = "inet_dgram_send", [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = "inet_raw_bind", [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = "inet_raw_send", [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = "unix_stream_bind", [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = "unix_stream_listen", [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = "unix_stream_connect", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = "unix_dgram_bind", [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = "unix_dgram_send", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = "unix_seqpacket_bind", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = "unix_seqpacket_listen", [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect", /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = "env", /* CONFIG group */ [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* String table for conditions. */ const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = { [TOMOYO_TASK_UID] = "task.uid", [TOMOYO_TASK_EUID] = "task.euid", [TOMOYO_TASK_SUID] = "task.suid", [TOMOYO_TASK_FSUID] = "task.fsuid", [TOMOYO_TASK_GID] = "task.gid", [TOMOYO_TASK_EGID] = "task.egid", [TOMOYO_TASK_SGID] = "task.sgid", [TOMOYO_TASK_FSGID] = "task.fsgid", [TOMOYO_TASK_PID] = "task.pid", [TOMOYO_TASK_PPID] = "task.ppid", [TOMOYO_EXEC_ARGC] = "exec.argc", [TOMOYO_EXEC_ENVC] = "exec.envc", [TOMOYO_TYPE_IS_SOCKET] = "socket", [TOMOYO_TYPE_IS_SYMLINK] = "symlink", [TOMOYO_TYPE_IS_FILE] = "file", [TOMOYO_TYPE_IS_BLOCK_DEV] = "block", [TOMOYO_TYPE_IS_DIRECTORY] = "directory", [TOMOYO_TYPE_IS_CHAR_DEV] = "char", [TOMOYO_TYPE_IS_FIFO] = "fifo", [TOMOYO_MODE_SETUID] = "setuid", [TOMOYO_MODE_SETGID] = "setgid", [TOMOYO_MODE_STICKY] = "sticky", [TOMOYO_MODE_OWNER_READ] = "owner_read", [TOMOYO_MODE_OWNER_WRITE] = "owner_write", [TOMOYO_MODE_OWNER_EXECUTE] = "owner_execute", [TOMOYO_MODE_GROUP_READ] = "group_read", [TOMOYO_MODE_GROUP_WRITE] = "group_write", [TOMOYO_MODE_GROUP_EXECUTE] = "group_execute", [TOMOYO_MODE_OTHERS_READ] = "others_read", [TOMOYO_MODE_OTHERS_WRITE] = "others_write", [TOMOYO_MODE_OTHERS_EXECUTE] = "others_execute", [TOMOYO_EXEC_REALPATH] = "exec.realpath", [TOMOYO_SYMLINK_TARGET] = "symlink.target", [TOMOYO_PATH1_UID] = "path1.uid", [TOMOYO_PATH1_GID] = "path1.gid", [TOMOYO_PATH1_INO] = "path1.ino", [TOMOYO_PATH1_MAJOR] = "path1.major", [TOMOYO_PATH1_MINOR] = "path1.minor", [TOMOYO_PATH1_PERM] = "path1.perm", [TOMOYO_PATH1_TYPE] = "path1.type", [TOMOYO_PATH1_DEV_MAJOR] = "path1.dev_major", [TOMOYO_PATH1_DEV_MINOR] = "path1.dev_minor", [TOMOYO_PATH2_UID] = "path2.uid", [TOMOYO_PATH2_GID] = "path2.gid", [TOMOYO_PATH2_INO] = "path2.ino", [TOMOYO_PATH2_MAJOR] = "path2.major", [TOMOYO_PATH2_MINOR] = "path2.minor", [TOMOYO_PATH2_PERM] = "path2.perm", [TOMOYO_PATH2_TYPE] = "path2.type", [TOMOYO_PATH2_DEV_MAJOR] = "path2.dev_major", [TOMOYO_PATH2_DEV_MINOR] = "path2.dev_minor", [TOMOYO_PATH1_PARENT_UID] = "path1.parent.uid", [TOMOYO_PATH1_PARENT_GID] = "path1.parent.gid", [TOMOYO_PATH1_PARENT_INO] = "path1.parent.ino", [TOMOYO_PATH1_PARENT_PERM] = "path1.parent.perm", [TOMOYO_PATH2_PARENT_UID] = "path2.parent.uid", [TOMOYO_PATH2_PARENT_GID] = "path2.parent.gid", [TOMOYO_PATH2_PARENT_INO] = "path2.parent.ino", [TOMOYO_PATH2_PARENT_PERM] = "path2.parent.perm", }; /* String table for PREFERENCE keyword. */ static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = { [TOMOYO_PREF_MAX_AUDIT_LOG] = "max_audit_log", [TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry", }; /* String table for path operation. */ const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = { [TOMOYO_TYPE_EXECUTE] = "execute", [TOMOYO_TYPE_READ] = "read", [TOMOYO_TYPE_WRITE] = "write", [TOMOYO_TYPE_APPEND] = "append", [TOMOYO_TYPE_UNLINK] = "unlink", [TOMOYO_TYPE_GETATTR] = "getattr", [TOMOYO_TYPE_RMDIR] = "rmdir", [TOMOYO_TYPE_TRUNCATE] = "truncate", [TOMOYO_TYPE_SYMLINK] = "symlink", [TOMOYO_TYPE_CHROOT] = "chroot", [TOMOYO_TYPE_UMOUNT] = "unmount", }; /* String table for socket's operation. */ const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = { [TOMOYO_NETWORK_BIND] = "bind", [TOMOYO_NETWORK_LISTEN] = "listen", [TOMOYO_NETWORK_CONNECT] = "connect", [TOMOYO_NETWORK_SEND] = "send", }; /* String table for categories. */ static const char * const tomoyo_category_keywords [TOMOYO_MAX_MAC_CATEGORY_INDEX] = { [TOMOYO_MAC_CATEGORY_FILE] = "file", [TOMOYO_MAC_CATEGORY_NETWORK] = "network", [TOMOYO_MAC_CATEGORY_MISC] = "misc", }; /* Permit policy management by non-root user? */ static bool tomoyo_manage_by_non_root; /* Utility functions. */ /** * tomoyo_addprintf - strncat()-like-snprintf(). * * @buffer: Buffer to write to. Must be '\0'-terminated. * @len: Size of @buffer. * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ __printf(3, 4) static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...) { va_list args; const int pos = strlen(buffer); va_start(args, fmt); vsnprintf(buffer + pos, len - pos - 1, fmt, args); va_end(args); } /** * tomoyo_flush - Flush queued string to userspace's buffer. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if all data was flushed, false otherwise. */ static bool tomoyo_flush(struct tomoyo_io_buffer *head) { while (head->r.w_pos) { const char *w = head->r.w[0]; size_t len = strlen(w); if (len) { if (len > head->read_user_buf_avail) len = head->read_user_buf_avail; if (!len) return false; if (copy_to_user(head->read_user_buf, w, len)) return false; head->read_user_buf_avail -= len; head->read_user_buf += len; w += len; } head->r.w[0] = w; if (*w) return false; /* Add '\0' for audit logs and query. */ if (head->poll) { if (!head->read_user_buf_avail || copy_to_user(head->read_user_buf, "", 1)) return false; head->read_user_buf_avail--; head->read_user_buf++; } head->r.w_pos--; for (len = 0; len < head->r.w_pos; len++) head->r.w[len] = head->r.w[len + 1]; } head->r.avail = 0; return true; } /** * tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @string: String to print. * * Note that @string has to be kept valid until @head is kfree()d. * This means that char[] allocated on stack memory cannot be passed to * this function. Use tomoyo_io_printf() for char[] allocated on stack memory. */ static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string) { if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) { head->r.w[head->r.w_pos++] = string; tomoyo_flush(head); } else WARN_ON(1); } static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) __printf(2, 3); /** * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * @fmt: The printf()'s format string, followed by parameters. */ static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt, ...) { va_list args; size_t len; size_t pos = head->r.avail; int size = head->readbuf_size - pos; if (size <= 0) return; va_start(args, fmt); len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1; va_end(args); if (pos + len >= head->readbuf_size) { WARN_ON(1); return; } head->r.avail += len; tomoyo_set_string(head, head->read_buf + pos); } /** * tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_space(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, " "); } /** * tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static bool tomoyo_set_lf(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "\n"); return !head->r.w_pos; } /** * tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_set_slash(struct tomoyo_io_buffer *head) { tomoyo_set_string(head, "/"); } /* List of namespaces. */ LIST_HEAD(tomoyo_namespace_list); /* True if namespace other than tomoyo_kernel_namespace is defined. */ static bool tomoyo_namespace_enabled; /** * tomoyo_init_policy_namespace - Initialize namespace. * * @ns: Pointer to "struct tomoyo_policy_namespace". * * Returns nothing. */ void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns) { unsigned int idx; for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++) INIT_LIST_HEAD(&ns->acl_group[idx]); for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++) INIT_LIST_HEAD(&ns->group_list[idx]); for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++) INIT_LIST_HEAD(&ns->policy_list[idx]); ns->profile_version = 20150505; tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list); list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list); } /** * tomoyo_print_namespace - Print namespace header. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_print_namespace(struct tomoyo_io_buffer *head) { if (!tomoyo_namespace_enabled) return; tomoyo_set_string(head, container_of(head->r.ns, struct tomoyo_policy_namespace, namespace_list)->name); tomoyo_set_space(head); } /** * tomoyo_print_name_union - Print a tomoyo_name_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". */ static void tomoyo_print_name_union(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { tomoyo_set_space(head); if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, ptr->filename->name); } } /** * tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns nothing. */ static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head, const struct tomoyo_name_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { tomoyo_set_string(head, "\""); tomoyo_set_string(head, ptr->filename->name); tomoyo_set_string(head, "\""); } } /** * tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union_nospace (struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { if (ptr->group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->group->group_name->name); } else { int i; unsigned long min = ptr->values[0]; const unsigned long max = ptr->values[1]; u8 min_type = ptr->value_type[0]; const u8 max_type = ptr->value_type[1]; char buffer[128]; buffer[0] = '\0'; for (i = 0; i < 2; i++) { switch (min_type) { case TOMOYO_VALUE_TYPE_HEXADECIMAL: tomoyo_addprintf(buffer, sizeof(buffer), "0x%lX", min); break; case TOMOYO_VALUE_TYPE_OCTAL: tomoyo_addprintf(buffer, sizeof(buffer), "0%lo", min); break; default: tomoyo_addprintf(buffer, sizeof(buffer), "%lu", min); break; } if (min == max && min_type == max_type) break; tomoyo_addprintf(buffer, sizeof(buffer), "-"); min_type = max_type; min = max; } tomoyo_io_printf(head, "%s", buffer); } } /** * tomoyo_print_number_union - Print a tomoyo_number_union. * * @head: Pointer to "struct tomoyo_io_buffer". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns nothing. */ static void tomoyo_print_number_union(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr) { tomoyo_set_space(head); tomoyo_print_number_union_nospace(head, ptr); } /** * tomoyo_assign_profile - Create a new profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to create. * * Returns pointer to "struct tomoyo_profile" on success, NULL otherwise. */ static struct tomoyo_profile *tomoyo_assign_profile (struct tomoyo_policy_namespace *ns, const unsigned int profile) { struct tomoyo_profile *ptr; struct tomoyo_profile *entry; if (profile >= TOMOYO_MAX_PROFILES) return NULL; ptr = ns->profile_ptr[profile]; if (ptr) return ptr; entry = kzalloc(sizeof(*entry), GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = ns->profile_ptr[profile]; if (!ptr && tomoyo_memory_ok(entry)) { ptr = entry; ptr->default_config = TOMOYO_CONFIG_DISABLED | TOMOYO_CONFIG_WANT_GRANT_LOG | TOMOYO_CONFIG_WANT_REJECT_LOG; memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT, sizeof(ptr->config)); ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] = CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG; ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] = CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY; mb(); /* Avoid out-of-order execution. */ ns->profile_ptr[profile] = ptr; entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_profile - Find a profile. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number to find. * * Returns pointer to "struct tomoyo_profile". */ struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns, const u8 profile) { static struct tomoyo_profile tomoyo_null_profile; struct tomoyo_profile *ptr = ns->profile_ptr[profile]; if (!ptr) ptr = &tomoyo_null_profile; return ptr; } /** * tomoyo_find_yesno - Find values for specified keyword. * * @string: String to check. * @find: Name of keyword. * * Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise. */ static s8 tomoyo_find_yesno(const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) { cp += strlen(find); if (!strncmp(cp, "=yes", 4)) return 1; else if (!strncmp(cp, "=no", 3)) return 0; } return -1; } /** * tomoyo_set_uint - Set value for specified preference. * * @i: Pointer to "unsigned int". * @string: String to check. * @find: Name of keyword. * * Returns nothing. */ static void tomoyo_set_uint(unsigned int *i, const char *string, const char *find) { const char *cp = strstr(string, find); if (cp) sscanf(cp + strlen(find), "=%u", i); } /** * tomoyo_set_mode - Set mode for specified profile. * * @name: Name of functionality. * @value: Mode for @name. * @profile: Pointer to "struct tomoyo_profile". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_set_mode(char *name, const char *value, struct tomoyo_profile *profile) { u8 i; u8 config; if (!strcmp(name, "CONFIG")) { i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; config = profile->default_config; } else if (tomoyo_str_starts(&name, "CONFIG::")) { config = 0; for (i = 0; i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) { int len = 0; if (i < TOMOYO_MAX_MAC_INDEX) { const u8 c = tomoyo_index2category[i]; const char *category = tomoyo_category_keywords[c]; len = strlen(category); if (strncmp(name, category, len) || name[len++] != ':' || name[len++] != ':') continue; } if (strcmp(name + len, tomoyo_mac_keywords[i])) continue; config = profile->config[i]; break; } if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) return -EINVAL; } else { return -EINVAL; } if (strstr(value, "use_default")) { config = TOMOYO_CONFIG_USE_DEFAULT; } else { u8 mode; for (mode = 0; mode < 4; mode++) if (strstr(value, tomoyo_mode[mode])) /* * Update lower 3 bits in order to distinguish * 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'. */ config = (config & ~7) | mode; if (config != TOMOYO_CONFIG_USE_DEFAULT) { switch (tomoyo_find_yesno(value, "grant_log")) { case 1: config |= TOMOYO_CONFIG_WANT_GRANT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG; break; } switch (tomoyo_find_yesno(value, "reject_log")) { case 1: config |= TOMOYO_CONFIG_WANT_REJECT_LOG; break; case 0: config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG; break; } } } if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) profile->config[i] = config; else if (config != TOMOYO_CONFIG_USE_DEFAULT) profile->default_config = config; return 0; } /** * tomoyo_write_profile - Write profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_write_profile(struct tomoyo_io_buffer *head) { char *data = head->write_buf; unsigned int i; char *cp; struct tomoyo_profile *profile; if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version) == 1) return 0; i = simple_strtoul(data, &cp, 10); if (*cp != '-') return -EINVAL; data = cp + 1; profile = tomoyo_assign_profile(head->w.ns, i); if (!profile) return -EINVAL; cp = strchr(data, '='); if (!cp) return -EINVAL; *cp++ = '\0'; if (!strcmp(data, "COMMENT")) { static DEFINE_SPINLOCK(lock); const struct tomoyo_path_info *new_comment = tomoyo_get_name(cp); const struct tomoyo_path_info *old_comment; if (!new_comment) return -ENOMEM; spin_lock(&lock); old_comment = profile->comment; profile->comment = new_comment; spin_unlock(&lock); tomoyo_put_name(old_comment); return 0; } if (!strcmp(data, "PREFERENCE")) { for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_set_uint(&profile->pref[i], cp, tomoyo_pref_keywords[i]); return 0; } return tomoyo_set_mode(data, cp, profile); } /** * tomoyo_print_config - Print mode for specified functionality. * * @head: Pointer to "struct tomoyo_io_buffer". * @config: Mode for that functionality. * * Returns nothing. * * Caller prints functionality's name. */ static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config) { tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n", tomoyo_mode[config & 3], str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG), str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG)); } /** * tomoyo_read_profile - Read profile table. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_profile(struct tomoyo_io_buffer *head) { u8 index; struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); const struct tomoyo_profile *profile; if (head->r.eof) return; next: index = head->r.index; profile = ns->profile_ptr[index]; switch (head->r.step) { case 0: tomoyo_print_namespace(head); tomoyo_io_printf(head, "PROFILE_VERSION=%u\n", ns->profile_version); head->r.step++; break; case 1: for ( ; head->r.index < TOMOYO_MAX_PROFILES; head->r.index++) if (ns->profile_ptr[head->r.index]) break; if (head->r.index == TOMOYO_MAX_PROFILES) { head->r.eof = true; return; } head->r.step++; break; case 2: { u8 i; const struct tomoyo_path_info *comment = profile->comment; tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-COMMENT=", index); tomoyo_set_string(head, comment ? comment->name : ""); tomoyo_set_lf(head); tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-PREFERENCE={ ", index); for (i = 0; i < TOMOYO_MAX_PREF; i++) tomoyo_io_printf(head, "%s=%u ", tomoyo_pref_keywords[i], profile->pref[i]); tomoyo_set_string(head, "}\n"); head->r.step++; } break; case 3: { tomoyo_print_namespace(head); tomoyo_io_printf(head, "%u-%s", index, "CONFIG"); tomoyo_print_config(head, profile->default_config); head->r.bit = 0; head->r.step++; } break; case 4: for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) { const u8 i = head->r.bit; const u8 config = profile->config[i]; if (config == TOMOYO_CONFIG_USE_DEFAULT) continue; tomoyo_print_namespace(head); if (i < TOMOYO_MAX_MAC_INDEX) tomoyo_io_printf(head, "%u-CONFIG::%s::%s", index, tomoyo_category_keywords [tomoyo_index2category[i]], tomoyo_mac_keywords[i]); else tomoyo_io_printf(head, "%u-CONFIG::%s", index, tomoyo_mac_keywords[i]); tomoyo_print_config(head, config); head->r.bit++; break; } if (head->r.bit == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX) { head->r.index++; head->r.step = 1; } break; } if (tomoyo_flush(head)) goto next; } /** * tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_manager(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { return container_of(a, struct tomoyo_manager, head)->manager == container_of(b, struct tomoyo_manager, head)->manager; } /** * tomoyo_update_manager_entry - Add a manager entry. * * @manager: The path to manager or the domainnamme. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_update_manager_entry(const char *manager, const bool is_delete) { struct tomoyo_manager e = { }; struct tomoyo_acl_param param = { /* .ns = &tomoyo_kernel_namespace, */ .is_delete = is_delete, .list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], }; int error = is_delete ? -ENOENT : -ENOMEM; if (!tomoyo_correct_domain(manager) && !tomoyo_correct_word(manager)) return -EINVAL; e.manager = tomoyo_get_name(manager); if (e.manager) { error = tomoyo_update_policy(&e.head, sizeof(e), ¶m, tomoyo_same_manager); tomoyo_put_name(e.manager); } return error; } /** * tomoyo_write_manager - Write manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_manager(struct tomoyo_io_buffer *head) { char *data = head->write_buf; if (!strcmp(data, "manage_by_non_root")) { tomoyo_manage_by_non_root = !head->w.is_delete; return 0; } return tomoyo_update_manager_entry(data, head->w.is_delete); } /** * tomoyo_read_manager - Read manager policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_manager(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) { struct tomoyo_manager *ptr = list_entry(head->r.acl, typeof(*ptr), head.list); if (ptr->head.is_deleted) continue; if (!tomoyo_flush(head)) return; tomoyo_set_string(head, ptr->manager->name); tomoyo_set_lf(head); } head->r.eof = true; } /** * tomoyo_manager - Check whether the current process is a policy manager. * * Returns true if the current process is permitted to modify policy * via /sys/kernel/security/tomoyo/ interface. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_manager(void) { struct tomoyo_manager *ptr; const char *exe; const struct task_struct *task = current; const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname; bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING); if (!tomoyo_policy_loaded) return true; if (!tomoyo_manage_by_non_root && (!uid_eq(task->cred->uid, GLOBAL_ROOT_UID) || !uid_eq(task->cred->euid, GLOBAL_ROOT_UID))) return false; exe = tomoyo_get_exe(); if (!exe) return false; list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list, srcu_read_lock_held(&tomoyo_ss)) { if (!ptr->head.is_deleted && (!tomoyo_pathcmp(domainname, ptr->manager) || !strcmp(exe, ptr->manager->name))) { found = true; break; } } if (!found) { /* Reduce error messages. */ static pid_t last_pid; const pid_t pid = current->pid; if (last_pid != pid) { pr_warn("%s ( %s ) is not permitted to update policies.\n", domainname->name, exe); last_pid = pid; } } kfree(exe); return found; } static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial); /** * tomoyo_select_domain - Parse select command. * * @head: Pointer to "struct tomoyo_io_buffer". * @data: String to parse. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, const char *data) { unsigned int pid; struct tomoyo_domain_info *domain = NULL; bool global_pid = false; if (strncmp(data, "select ", 7)) return false; data += 7; if (sscanf(data, "pid=%u", &pid) == 1 || (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) { struct task_struct *p; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) domain = tomoyo_find_domain(data + 7); } else if (sscanf(data, "Q=%u", &pid) == 1) { domain = tomoyo_find_domain_by_qid(pid); } else return false; head->w.domain = domain; /* Accessing read_buf is safe because head->io_sem is held. */ if (!head->read_buf) return true; /* Do nothing if open(O_WRONLY). */ memset(&head->r, 0, sizeof(head->r)); head->r.print_this_domain_only = true; if (domain) head->r.domain = &domain->list; else head->r.eof = true; tomoyo_io_printf(head, "# select %s\n", data); if (domain && domain->is_deleted) tomoyo_io_printf(head, "# This is a deleted domain.\n"); return true; } /** * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head); return p1->domainname == p2->domainname; } /** * tomoyo_write_task - Update task related list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_task(struct tomoyo_acl_param *param) { int error = -EINVAL; if (tomoyo_str_starts(¶m->data, "manual_domain_transition ")) { struct tomoyo_task_acl e = { .head.type = TOMOYO_TYPE_MANUAL_TASK_ACL, .domainname = tomoyo_get_domainname(param), }; if (e.domainname) error = tomoyo_update_domain(&e.head, sizeof(e), param, tomoyo_same_task_acl, NULL); tomoyo_put_name(e.domainname); } return error; } /** * tomoyo_delete_domain - Delete a domain. * * @domainname: The name of domain. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_delete_domain(char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -EINTR; /* Is there an active domain? */ list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { /* Never delete tomoyo_kernel_domain */ if (domain == &tomoyo_kernel_domain) continue; if (domain->is_deleted || tomoyo_pathcmp(domain->domainname, &name)) continue; domain->is_deleted = true; break; } mutex_unlock(&tomoyo_policy_lock); return 0; } /** * tomoyo_write_domain2 - Write domain policy. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @list: Pointer to "struct list_head". * @data: Policy to be interpreted. * @is_delete: True if it is a delete request. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns, struct list_head *list, char *data, const bool is_delete) { struct tomoyo_acl_param param = { .ns = ns, .list = list, .data = data, .is_delete = is_delete, }; static const struct { const char *keyword; int (*write)(struct tomoyo_acl_param *param); } tomoyo_callback[5] = { { "file ", tomoyo_write_file }, { "network inet ", tomoyo_write_inet_network }, { "network unix ", tomoyo_write_unix_network }, { "misc ", tomoyo_write_misc }, { "task ", tomoyo_write_task }, }; u8 i; for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) { if (!tomoyo_str_starts(¶m.data, tomoyo_callback[i].keyword)) continue; return tomoyo_callback[i].write(¶m); } return -EINVAL; } /* String table for domain flags. */ const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = { [TOMOYO_DIF_QUOTA_WARNED] = "quota_exceeded\n", [TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n", }; /** * tomoyo_write_domain - Write domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_domain(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct tomoyo_policy_namespace *ns; struct tomoyo_domain_info *domain = head->w.domain; const bool is_delete = head->w.is_delete; bool is_select = !is_delete && tomoyo_str_starts(&data, "select "); unsigned int idx; if (*data == '<') { int ret = 0; domain = NULL; if (is_delete) ret = tomoyo_delete_domain(data); else if (is_select) domain = tomoyo_find_domain(data); else domain = tomoyo_assign_domain(data, false); head->w.domain = domain; return ret; } if (!domain) return -EINVAL; ns = domain->ns; if (sscanf(data, "use_profile %u", &idx) == 1 && idx < TOMOYO_MAX_PROFILES) { if (!tomoyo_policy_loaded || ns->profile_ptr[idx]) if (!is_delete) domain->profile = (u8) idx; return 0; } if (sscanf(data, "use_group %u\n", &idx) == 1 && idx < TOMOYO_MAX_ACL_GROUPS) { if (!is_delete) set_bit(idx, domain->group); else clear_bit(idx, domain->group); return 0; } for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) { const char *cp = tomoyo_dif[idx]; if (strncmp(data, cp, strlen(cp) - 1)) continue; domain->flags[idx] = !is_delete; return 0; } return tomoyo_write_domain2(ns, &domain->acl_info_list, data, is_delete); } /** * tomoyo_print_condition - Print condition part. * * @head: Pointer to "struct tomoyo_io_buffer". * @cond: Pointer to "struct tomoyo_condition". * * Returns true on success, false otherwise. */ static bool tomoyo_print_condition(struct tomoyo_io_buffer *head, const struct tomoyo_condition *cond) { switch (head->r.cond_step) { case 0: head->r.cond_index = 0; head->r.cond_step++; if (cond->transit) { tomoyo_set_space(head); tomoyo_set_string(head, cond->transit->name); } fallthrough; case 1: { const u16 condc = cond->condc; const struct tomoyo_condition_element *condp = (typeof(condp)) (cond + 1); const struct tomoyo_number_union *numbers_p = (typeof(numbers_p)) (condp + condc); const struct tomoyo_name_union *names_p = (typeof(names_p)) (numbers_p + cond->numbers_count); const struct tomoyo_argv *argv = (typeof(argv)) (names_p + cond->names_count); const struct tomoyo_envp *envp = (typeof(envp)) (argv + cond->argc); u16 skip; for (skip = 0; skip < head->r.cond_index; skip++) { const u8 left = condp->left; const u8 right = condp->right; condp++; switch (left) { case TOMOYO_ARGV_ENTRY: argv++; continue; case TOMOYO_ENVP_ENTRY: envp++; continue; case TOMOYO_NUMBER_UNION: numbers_p++; break; } switch (right) { case TOMOYO_NAME_UNION: names_p++; break; case TOMOYO_NUMBER_UNION: numbers_p++; break; } } while (head->r.cond_index < condc) { const u8 match = condp->equals; const u8 left = condp->left; const u8 right = condp->right; if (!tomoyo_flush(head)) return false; condp++; head->r.cond_index++; tomoyo_set_space(head); switch (left) { case TOMOYO_ARGV_ENTRY: tomoyo_io_printf(head, "exec.argv[%lu]%s=\"", argv->index, argv->is_not ? "!" : ""); tomoyo_set_string(head, argv->value->name); tomoyo_set_string(head, "\""); argv++; continue; case TOMOYO_ENVP_ENTRY: tomoyo_set_string(head, "exec.envp[\""); tomoyo_set_string(head, envp->name->name); tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : ""); if (envp->value) { tomoyo_set_string(head, "\""); tomoyo_set_string(head, envp->value->name); tomoyo_set_string(head, "\""); } else { tomoyo_set_string(head, "NULL"); } envp++; continue; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[left]); break; } tomoyo_set_string(head, match ? "=" : "!="); switch (right) { case TOMOYO_NAME_UNION: tomoyo_print_name_union_quoted (head, names_p++); break; case TOMOYO_NUMBER_UNION: tomoyo_print_number_union_nospace (head, numbers_p++); break; default: tomoyo_set_string(head, tomoyo_condition_keyword[right]); break; } } } head->r.cond_step++; fallthrough; case 2: if (!tomoyo_flush(head)) break; head->r.cond_step++; fallthrough; case 3: if (cond->grant_log != TOMOYO_GRANTLOG_AUTO) tomoyo_io_printf(head, " grant_log=%s", str_yes_no(cond->grant_log == TOMOYO_GRANTLOG_YES)); tomoyo_set_lf(head); return true; } return false; } /** * tomoyo_set_group - Print "acl_group " header keyword and category name. * * @head: Pointer to "struct tomoyo_io_buffer". * @category: Category name. * * Returns nothing. */ static void tomoyo_set_group(struct tomoyo_io_buffer *head, const char *category) { if (head->type == TOMOYO_EXCEPTIONPOLICY) { tomoyo_print_namespace(head); tomoyo_io_printf(head, "acl_group %u ", head->r.acl_group_index); } tomoyo_set_string(head, category); } /** * tomoyo_print_entry - Print an ACL entry. * * @head: Pointer to "struct tomoyo_io_buffer". * @acl: Pointer to an ACL entry. * * Returns true on success, false otherwise. */ static bool tomoyo_print_entry(struct tomoyo_io_buffer *head, struct tomoyo_acl_info *acl) { const u8 acl_type = acl->type; bool first = true; u8 bit; if (head->r.print_cond_part) goto print_cond_part; if (acl->is_deleted) return true; if (!tomoyo_flush(head)) return false; else if (acl_type == TOMOYO_TYPE_PATH_ACL) { struct tomoyo_path_acl *ptr = container_of(acl, typeof(*ptr), head); const u16 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (head->r.print_transition_related_only && bit != TOMOYO_TYPE_EXECUTE) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_path_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) { struct tomoyo_task_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "task "); tomoyo_set_string(head, "manual_domain_transition "); tomoyo_set_string(head, ptr->domainname->name); } else if (head->r.print_transition_related_only) { return true; } else if (acl_type == TOMOYO_TYPE_PATH2_ACL) { struct tomoyo_path2_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pp2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name1); tomoyo_print_name_union(head, &ptr->name2); } else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) { struct tomoyo_path_number_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->number); } else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) { struct tomoyo_mkdev_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "file "); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_mac_keywords [tomoyo_pnnn2mac[bit]]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); tomoyo_print_number_union(head, &ptr->mode); tomoyo_print_number_union(head, &ptr->major); tomoyo_print_number_union(head, &ptr->minor); } else if (acl_type == TOMOYO_TYPE_INET_ACL) { struct tomoyo_inet_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network inet "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_set_space(head); if (ptr->address.group) { tomoyo_set_string(head, "@"); tomoyo_set_string(head, ptr->address.group->group_name ->name); } else { char buf[128]; tomoyo_print_ip(buf, sizeof(buf), &ptr->address); tomoyo_io_printf(head, "%s", buf); } tomoyo_print_number_union(head, &ptr->port); } else if (acl_type == TOMOYO_TYPE_UNIX_ACL) { struct tomoyo_unix_acl *ptr = container_of(acl, typeof(*ptr), head); const u8 perm = ptr->perm; for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) { if (!(perm & (1 << bit))) continue; if (first) { tomoyo_set_group(head, "network unix "); tomoyo_set_string(head, tomoyo_proto_keyword [ptr->protocol]); tomoyo_set_space(head); first = false; } else { tomoyo_set_slash(head); } tomoyo_set_string(head, tomoyo_socket_keyword[bit]); } if (first) return true; tomoyo_print_name_union(head, &ptr->name); } else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) { struct tomoyo_mount_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "file mount"); tomoyo_print_name_union(head, &ptr->dev_name); tomoyo_print_name_union(head, &ptr->dir_name); tomoyo_print_name_union(head, &ptr->fs_type); tomoyo_print_number_union(head, &ptr->flags); } else if (acl_type == TOMOYO_TYPE_ENV_ACL) { struct tomoyo_env_acl *ptr = container_of(acl, typeof(*ptr), head); tomoyo_set_group(head, "misc env "); tomoyo_set_string(head, ptr->env->name); } if (acl->cond) { head->r.print_cond_part = true; head->r.cond_step = 0; if (!tomoyo_flush(head)) return false; print_cond_part: if (!tomoyo_print_condition(head, acl->cond)) return false; head->r.print_cond_part = false; } else { tomoyo_set_lf(head); } return true; } /** * tomoyo_read_domain2 - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * @list: Pointer to "struct list_head". * * Caller holds tomoyo_read_lock(). * * Returns true on success, false otherwise. */ static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head, struct list_head *list) { list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_info *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (!tomoyo_print_entry(head, ptr)) return false; } head->r.acl = NULL; return true; } /** * tomoyo_read_domain - Read domain policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_domain(struct tomoyo_io_buffer *head) { if (head->r.eof) return; list_for_each_cookie(head->r.domain, &tomoyo_domain_list) { struct tomoyo_domain_info *domain = list_entry(head->r.domain, typeof(*domain), list); u8 i; switch (head->r.step) { case 0: if (domain->is_deleted && !head->r.print_this_domain_only) continue; /* Print domainname and flags. */ tomoyo_set_string(head, domain->domainname->name); tomoyo_set_lf(head); tomoyo_io_printf(head, "use_profile %u\n", domain->profile); for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++) if (domain->flags[i]) tomoyo_set_string(head, tomoyo_dif[i]); head->r.index = 0; head->r.step++; fallthrough; case 1: while (head->r.index < TOMOYO_MAX_ACL_GROUPS) { i = head->r.index++; if (!test_bit(i, domain->group)) continue; tomoyo_io_printf(head, "use_group %u\n", i); if (!tomoyo_flush(head)) return; } head->r.index = 0; head->r.step++; tomoyo_set_lf(head); fallthrough; case 2: if (!tomoyo_read_domain2(head, &domain->acl_info_list)) return; head->r.step++; if (!tomoyo_set_lf(head)) return; fallthrough; case 3: head->r.step = 0; if (head->r.print_this_domain_only) goto done; } } done: head->r.eof = true; } /** * tomoyo_write_pid: Specify PID to obtain domainname. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_pid(struct tomoyo_io_buffer *head) { head->r.eof = false; return 0; } /** * tomoyo_read_pid - Get domainname of the specified PID. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns the domainname which the specified PID is in on success, * empty string otherwise. * The PID is specified by tomoyo_write_pid() so that the user can obtain * using read()/write() interface rather than sysctl() interface. */ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) { char *buf = head->write_buf; bool global_pid = false; unsigned int pid; struct task_struct *p; struct tomoyo_domain_info *domain = NULL; /* Accessing write_buf is safe because head->io_sem is held. */ if (!buf) { head->r.eof = true; return; /* Do nothing if open(O_RDONLY). */ } if (head->r.w_pos || head->r.eof) return; head->r.eof = true; if (tomoyo_str_starts(&buf, "global-pid ")) global_pid = true; if (kstrtouint(buf, 10, &pid)) return; rcu_read_lock(); if (global_pid) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); if (p) domain = tomoyo_task(p)->domain_info; rcu_read_unlock(); if (!domain) return; tomoyo_io_printf(head, "%u %u ", pid, domain->profile); tomoyo_set_string(head, domain->domainname->name); } /* String table for domain transition control keywords. */ static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = { [TOMOYO_TRANSITION_CONTROL_NO_RESET] = "no_reset_domain ", [TOMOYO_TRANSITION_CONTROL_RESET] = "reset_domain ", [TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ", [TOMOYO_TRANSITION_CONTROL_INITIALIZE] = "initialize_domain ", [TOMOYO_TRANSITION_CONTROL_NO_KEEP] = "no_keep_domain ", [TOMOYO_TRANSITION_CONTROL_KEEP] = "keep_domain ", }; /* String table for grouping keywords. */ static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = { [TOMOYO_PATH_GROUP] = "path_group ", [TOMOYO_NUMBER_GROUP] = "number_group ", [TOMOYO_ADDRESS_GROUP] = "address_group ", }; /** * tomoyo_write_exception - Write exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_write_exception(struct tomoyo_io_buffer *head) { const bool is_delete = head->w.is_delete; struct tomoyo_acl_param param = { .ns = head->w.ns, .is_delete = is_delete, .data = head->write_buf, }; u8 i; if (tomoyo_str_starts(¶m.data, "aggregator ")) return tomoyo_write_aggregator(¶m); for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++) if (tomoyo_str_starts(¶m.data, tomoyo_transition_type[i])) return tomoyo_write_transition_control(¶m, i); for (i = 0; i < TOMOYO_MAX_GROUP; i++) if (tomoyo_str_starts(¶m.data, tomoyo_group_name[i])) return tomoyo_write_group(¶m, i); if (tomoyo_str_starts(¶m.data, "acl_group ")) { unsigned int group; char *data; group = simple_strtoul(param.data, &data, 10); if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ') return tomoyo_write_domain2 (head->w.ns, &head->w.ns->acl_group[group], data, is_delete); } return -EINVAL; } /** * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->group_list[idx]; list_for_each_cookie(head->r.group, list) { struct tomoyo_group *group = list_entry(head->r.group, typeof(*group), head.list); list_for_each_cookie(head->r.acl, &group->member_list) { struct tomoyo_acl_head *ptr = list_entry(head->r.acl, typeof(*ptr), list); if (ptr->is_deleted) continue; if (!tomoyo_flush(head)) return false; tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_group_name[idx]); tomoyo_set_string(head, group->group_name->name); if (idx == TOMOYO_PATH_GROUP) { tomoyo_set_space(head); tomoyo_set_string(head, container_of (ptr, struct tomoyo_path_group, head)->member_name->name); } else if (idx == TOMOYO_NUMBER_GROUP) { tomoyo_print_number_union(head, &container_of (ptr, struct tomoyo_number_group, head)->number); } else if (idx == TOMOYO_ADDRESS_GROUP) { char buffer[128]; struct tomoyo_address_group *member = container_of(ptr, typeof(*member), head); tomoyo_print_ip(buffer, sizeof(buffer), &member->address); tomoyo_io_printf(head, " %s", buffer); } tomoyo_set_lf(head); } head->r.acl = NULL; } head->r.group = NULL; return true; } /** * tomoyo_read_policy - Read "struct tomoyo_..._entry" list. * * @head: Pointer to "struct tomoyo_io_buffer". * @idx: Index number. * * Returns true on success, false otherwise. * * Caller holds tomoyo_read_lock(). */ static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); struct list_head *list = &ns->policy_list[idx]; list_for_each_cookie(head->r.acl, list) { struct tomoyo_acl_head *acl = container_of(head->r.acl, typeof(*acl), list); if (acl->is_deleted) continue; if (!tomoyo_flush(head)) return false; switch (idx) { case TOMOYO_ID_TRANSITION_CONTROL: { struct tomoyo_transition_control *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, tomoyo_transition_type [ptr->type]); tomoyo_set_string(head, ptr->program ? ptr->program->name : "any"); tomoyo_set_string(head, " from "); tomoyo_set_string(head, ptr->domainname ? ptr->domainname->name : "any"); } break; case TOMOYO_ID_AGGREGATOR: { struct tomoyo_aggregator *ptr = container_of(acl, typeof(*ptr), head); tomoyo_print_namespace(head); tomoyo_set_string(head, "aggregator "); tomoyo_set_string(head, ptr->original_name->name); tomoyo_set_space(head); tomoyo_set_string(head, ptr->aggregated_name->name); } break; default: continue; } tomoyo_set_lf(head); } head->r.acl = NULL; return true; } /** * tomoyo_read_exception - Read exception policy. * * @head: Pointer to "struct tomoyo_io_buffer". * * Caller holds tomoyo_read_lock(). */ static void tomoyo_read_exception(struct tomoyo_io_buffer *head) { struct tomoyo_policy_namespace *ns = container_of(head->r.ns, typeof(*ns), namespace_list); if (head->r.eof) return; while (head->r.step < TOMOYO_MAX_POLICY && tomoyo_read_policy(head, head->r.step)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP && tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY)) head->r.step++; if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP) return; while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP + TOMOYO_MAX_ACL_GROUPS) { head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY - TOMOYO_MAX_GROUP; if (!tomoyo_read_domain2(head, &ns->acl_group [head->r.acl_group_index])) return; head->r.step++; } head->r.eof = true; } /* Wait queue for kernel -> userspace notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait); /* Wait queue for userspace -> kernel notification. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait); /* Structure for query. */ struct tomoyo_query { struct list_head list; struct tomoyo_domain_info *domain; char *query; size_t query_len; unsigned int serial; u8 timer; u8 answer; u8 retry; }; /* The list for "struct tomoyo_query". */ static LIST_HEAD(tomoyo_query_list); /* Lock for manipulating tomoyo_query_list. */ static DEFINE_SPINLOCK(tomoyo_query_list_lock); /* * Number of "struct file" referring /sys/kernel/security/tomoyo/query * interface. */ static atomic_t tomoyo_query_observers = ATOMIC_INIT(0); /** * tomoyo_truncate - Truncate a line. * * @str: String to truncate. * * Returns length of truncated @str. */ static int tomoyo_truncate(char *str) { char *start = str; while (*(unsigned char *) str > (unsigned char) ' ') str++; *str = '\0'; return strlen(start) + 1; } /** * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode. * * @domain: Pointer to "struct tomoyo_domain_info". * @header: Lines containing ACL. * * Returns nothing. */ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) { char *buffer; char *realpath = NULL; char *argv0 = NULL; char *symlink = NULL; char *cp = strchr(header, '\n'); int len; if (!cp) return; cp = strchr(cp + 1, '\n'); if (!cp) return; *cp++ = '\0'; len = strlen(cp) + 1; /* strstr() will return NULL if ordering is wrong. */ if (*cp == 'f') { argv0 = strstr(header, " argv[]={ \""); if (argv0) { argv0 += 10; len += tomoyo_truncate(argv0) + 14; } realpath = strstr(header, " exec={ realpath=\""); if (realpath) { realpath += 8; len += tomoyo_truncate(realpath) + 6; } symlink = strstr(header, " symlink.target=\""); if (symlink) len += tomoyo_truncate(symlink + 1) + 1; } buffer = kmalloc(len, GFP_NOFS); if (!buffer) return; snprintf(buffer, len - 1, "%s", cp); if (*cp == 'f' && strchr(buffer, ':')) { /* Automatically replace 2 or more digits with \$ pattern. */ char *cp2; /* e.g. file read proc:/$PID/stat */ cp = strstr(buffer, " proc:/"); if (cp && simple_strtoul(cp + 7, &cp2, 10) >= 10 && *cp2 == '/') { *(cp + 7) = '\\'; *(cp + 8) = '$'; memmove(cp + 9, cp2, strlen(cp2) + 1); goto ok; } /* e.g. file ioctl pipe:[$INO] $CMD */ cp = strstr(buffer, " pipe:["); if (cp && simple_strtoul(cp + 7, &cp2, 10) >= 10 && *cp2 == ']') { *(cp + 7) = '\\'; *(cp + 8) = '$'; memmove(cp + 9, cp2, strlen(cp2) + 1); goto ok; } /* e.g. file ioctl socket:[$INO] $CMD */ cp = strstr(buffer, " socket:["); if (cp && simple_strtoul(cp + 9, &cp2, 10) >= 10 && *cp2 == ']') { *(cp + 9) = '\\'; *(cp + 10) = '$'; memmove(cp + 11, cp2, strlen(cp2) + 1); goto ok; } } ok: if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0); if (symlink) tomoyo_addprintf(buffer, len, "%s", symlink); tomoyo_normalize_line(buffer); if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer, false)) tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); kfree(buffer); } /** * tomoyo_supervisor - Ask for the supervisor's decision. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns 0 if the supervisor decided to permit the access request which * violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the * supervisor decided to retry the access request which violated the policy in * enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise. */ int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int error; int len; static unsigned int tomoyo_serial; struct tomoyo_query entry = { }; bool quota_exceeded = false; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); /* Write /sys/kernel/security/tomoyo/audit. */ va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); /* Nothing more to do if granted. */ if (r->granted) return 0; if (r->mode) tomoyo_update_stat(r->mode); switch (r->mode) { case TOMOYO_CONFIG_ENFORCING: error = -EPERM; if (atomic_read(&tomoyo_query_observers)) break; goto out; case TOMOYO_CONFIG_LEARNING: error = 0; /* Check max_learning_entry parameter. */ if (tomoyo_domain_quota_is_ok(r)) break; fallthrough; default: return 0; } /* Get message. */ va_start(args, fmt); entry.query = tomoyo_init_log(r, len, fmt, args); va_end(args); if (!entry.query) goto out; entry.query_len = strlen(entry.query) + 1; if (!error) { tomoyo_add_entry(r->domain, entry.query); goto out; } len = kmalloc_size_roundup(entry.query_len); entry.domain = r->domain; spin_lock(&tomoyo_query_list_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] && tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len >= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) { quota_exceeded = true; } else { entry.serial = tomoyo_serial++; entry.retry = r->retry; tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len; list_add_tail(&entry.list, &tomoyo_query_list); } spin_unlock(&tomoyo_query_list_lock); if (quota_exceeded) goto out; /* Give 10 seconds for supervisor's opinion. */ while (entry.timer < 10) { wake_up_all(&tomoyo_query_wait); if (wait_event_interruptible_timeout (tomoyo_answer_wait, entry.answer || !atomic_read(&tomoyo_query_observers), HZ)) break; entry.timer++; } spin_lock(&tomoyo_query_list_lock); list_del(&entry.list); tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len; spin_unlock(&tomoyo_query_list_lock); switch (entry.answer) { case 3: /* Asked to retry by administrator. */ error = TOMOYO_RETRY_REQUEST; r->retry++; break; case 1: /* Granted by administrator. */ error = 0; break; default: /* Timed out or rejected by administrator. */ break; } out: kfree(entry.query); return error; } /** * tomoyo_find_domain_by_qid - Get domain by query id. * * @serial: Query ID assigned by tomoyo_supervisor(). * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. */ static struct tomoyo_domain_info *tomoyo_find_domain_by_qid (unsigned int serial) { struct tomoyo_query *ptr; struct tomoyo_domain_info *domain = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each_entry(ptr, &tomoyo_query_list, list) { if (ptr->serial != serial) continue; domain = ptr->domain; break; } spin_unlock(&tomoyo_query_list_lock); return domain; } /** * tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". * * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise. * * Waits for access requests which violated policy in enforcing mode. */ static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait) { if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_query_wait, wait); if (!list_empty(&tomoyo_query_list)) return EPOLLIN | EPOLLRDNORM; return 0; } /** * tomoyo_read_query - Read access requests which violated policy in enforcing mode. * * @head: Pointer to "struct tomoyo_io_buffer". */ static void tomoyo_read_query(struct tomoyo_io_buffer *head) { struct list_head *tmp; unsigned int pos = 0; size_t len = 0; char *buf; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; len = ptr->query_len; break; } spin_unlock(&tomoyo_query_list_lock); if (!len) { head->r.query_index = 0; return; } buf = kzalloc(len + 32, GFP_NOFS); if (!buf) return; pos = 0; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (pos++ != head->r.query_index) continue; /* * Some query can be skipped because tomoyo_query_list * can change, but I don't care. */ if (len == ptr->query_len) snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial, ptr->retry, ptr->query); break; } spin_unlock(&tomoyo_query_list_lock); if (buf[0]) { head->read_buf = buf; head->r.w[head->r.w_pos++] = buf; head->r.query_index++; } else { kfree(buf); } } /** * tomoyo_write_answer - Write the supervisor's decision. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0 on success, -EINVAL otherwise. */ static int tomoyo_write_answer(struct tomoyo_io_buffer *head) { char *data = head->write_buf; struct list_head *tmp; unsigned int serial; unsigned int answer; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); ptr->timer = 0; } spin_unlock(&tomoyo_query_list_lock); if (sscanf(data, "A%u=%u", &serial, &answer) != 2) return -EINVAL; spin_lock(&tomoyo_query_list_lock); list_for_each(tmp, &tomoyo_query_list) { struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list); if (ptr->serial != serial) continue; ptr->answer = answer; /* Remove from tomoyo_query_list. */ if (ptr->answer) list_del_init(&ptr->list); break; } spin_unlock(&tomoyo_query_list_lock); return 0; } /** * tomoyo_read_version: Get version. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns version information. */ static void tomoyo_read_version(struct tomoyo_io_buffer *head) { if (!head->r.eof) { tomoyo_io_printf(head, "2.6.0"); head->r.eof = true; } } /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = { [TOMOYO_STAT_POLICY_UPDATES] = "update:", [TOMOYO_STAT_POLICY_LEARNING] = "violation in learning mode:", [TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:", [TOMOYO_STAT_POLICY_ENFORCING] = "violation in enforcing mode:", }; /* String table for /sys/kernel/security/tomoyo/stat interface. */ static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = { [TOMOYO_MEMORY_POLICY] = "policy:", [TOMOYO_MEMORY_AUDIT] = "audit log:", [TOMOYO_MEMORY_QUERY] = "query message:", }; /* Counter for number of updates. */ static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT]; /* Timestamp counter for last updated. */ static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT]; /** * tomoyo_update_stat - Update statistic counters. * * @index: Index for policy type. * * Returns nothing. */ void tomoyo_update_stat(const u8 index) { atomic_inc(&tomoyo_stat_updated[index]); tomoyo_stat_modified[index] = ktime_get_real_seconds(); } /** * tomoyo_read_stat - Read statistic data. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static void tomoyo_read_stat(struct tomoyo_io_buffer *head) { u8 i; unsigned int total = 0; if (head->r.eof) return; for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) { tomoyo_io_printf(head, "Policy %-30s %10u", tomoyo_policy_headers[i], atomic_read(&tomoyo_stat_updated[i])); if (tomoyo_stat_modified[i]) { struct tomoyo_time stamp; tomoyo_convert_time(tomoyo_stat_modified[i], &stamp); tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec); } tomoyo_set_lf(head); } for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) { unsigned int used = tomoyo_memory_used[i]; total += used; tomoyo_io_printf(head, "Memory used by %-22s %10u", tomoyo_memory_headers[i], used); used = tomoyo_memory_quota[i]; if (used) tomoyo_io_printf(head, " (Quota: %10u)", used); tomoyo_set_lf(head); } tomoyo_io_printf(head, "Total memory used: %10u\n", total); head->r.eof = true; } /** * tomoyo_write_stat - Set memory quota. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns 0. */ static int tomoyo_write_stat(struct tomoyo_io_buffer *head) { char *data = head->write_buf; u8 i; if (tomoyo_str_starts(&data, "Memory used by ")) for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) if (tomoyo_str_starts(&data, tomoyo_memory_headers[i])) sscanf(data, "%u", &tomoyo_memory_quota[i]); return 0; } /** * tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface. * * @type: Type of interface. * @file: Pointer to "struct file". * * Returns 0 on success, negative value otherwise. */ int tomoyo_open_control(const u8 type, struct file *file) { struct tomoyo_io_buffer *head = kzalloc(sizeof(*head), GFP_NOFS); if (!head) return -ENOMEM; mutex_init(&head->io_sem); head->type = type; switch (type) { case TOMOYO_DOMAINPOLICY: /* /sys/kernel/security/tomoyo/domain_policy */ head->write = tomoyo_write_domain; head->read = tomoyo_read_domain; break; case TOMOYO_EXCEPTIONPOLICY: /* /sys/kernel/security/tomoyo/exception_policy */ head->write = tomoyo_write_exception; head->read = tomoyo_read_exception; break; case TOMOYO_AUDIT: /* /sys/kernel/security/tomoyo/audit */ head->poll = tomoyo_poll_log; head->read = tomoyo_read_log; break; case TOMOYO_PROCESS_STATUS: /* /sys/kernel/security/tomoyo/.process_status */ head->write = tomoyo_write_pid; head->read = tomoyo_read_pid; break; case TOMOYO_VERSION: /* /sys/kernel/security/tomoyo/version */ head->read = tomoyo_read_version; head->readbuf_size = 128; break; case TOMOYO_STAT: /* /sys/kernel/security/tomoyo/stat */ head->write = tomoyo_write_stat; head->read = tomoyo_read_stat; head->readbuf_size = 1024; break; case TOMOYO_PROFILE: /* /sys/kernel/security/tomoyo/profile */ head->write = tomoyo_write_profile; head->read = tomoyo_read_profile; break; case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */ head->poll = tomoyo_poll_query; head->write = tomoyo_write_answer; head->read = tomoyo_read_query; break; case TOMOYO_MANAGER: /* /sys/kernel/security/tomoyo/manager */ head->write = tomoyo_write_manager; head->read = tomoyo_read_manager; break; } if (!(file->f_mode & FMODE_READ)) { /* * No need to allocate read_buf since it is not opened * for reading. */ head->read = NULL; head->poll = NULL; } else if (!head->poll) { /* Don't allocate read_buf for poll() access. */ if (!head->readbuf_size) head->readbuf_size = 4096 * 2; head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS); if (!head->read_buf) { kfree(head); return -ENOMEM; } } if (!(file->f_mode & FMODE_WRITE)) { /* * No need to allocate write_buf since it is not opened * for writing. */ head->write = NULL; } else if (head->write) { head->writebuf_size = 4096 * 2; head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS); if (!head->write_buf) { kfree(head->read_buf); kfree(head); return -ENOMEM; } } /* * If the file is /sys/kernel/security/tomoyo/query , increment the * observer counter. * The obserber counter is used by tomoyo_supervisor() to see if * there is some process monitoring /sys/kernel/security/tomoyo/query. */ if (type == TOMOYO_QUERY) atomic_inc(&tomoyo_query_observers); file->private_data = head; tomoyo_notify_gc(head, true); return 0; } /** * tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, * EPOLLOUT | EPOLLWRNORM otherwise. */ __poll_t tomoyo_poll_control(struct file *file, poll_table *wait) { struct tomoyo_io_buffer *head = file->private_data; if (head->poll) return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM; return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM; } /** * tomoyo_set_namespace_cursor - Set namespace to read. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head) { struct list_head *ns; if (head->type != TOMOYO_EXCEPTIONPOLICY && head->type != TOMOYO_PROFILE) return; /* * If this is the first read, or reading previous namespace finished * and has more namespaces to read, update the namespace cursor. */ ns = head->r.ns; if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) { /* Clearing is OK because tomoyo_flush() returned true. */ memset(&head->r, 0, sizeof(head->r)); head->r.ns = ns ? ns->next : tomoyo_namespace_list.next; } } /** * tomoyo_has_more_namespace - Check for unread namespaces. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns true if we have more entries to print, false otherwise. */ static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head) { return (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) && head->r.eof && head->r.ns->next != &tomoyo_namespace_list; } /** * tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to write to. * @buffer_len: Size of @buffer. * * Returns bytes read on success, negative value otherwise. */ ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer, const int buffer_len) { int len; int idx; if (!head->read) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; head->read_user_buf = buffer; head->read_user_buf_avail = buffer_len; idx = tomoyo_read_lock(); if (tomoyo_flush(head)) /* Call the policy handler. */ do { tomoyo_set_namespace_cursor(head); head->read(head); } while (tomoyo_flush(head) && tomoyo_has_more_namespace(head)); tomoyo_read_unlock(idx); len = head->read_user_buf - buffer; mutex_unlock(&head->io_sem); return len; } /** * tomoyo_parse_policy - Parse a policy line. * * @head: Pointer to "struct tomoyo_io_buffer". * @line: Line to parse. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line) { /* Delete request? */ head->w.is_delete = !strncmp(line, "delete ", 7); if (head->w.is_delete) memmove(line, line + 7, strlen(line + 7) + 1); /* Selecting namespace to update. */ if (head->type == TOMOYO_EXCEPTIONPOLICY || head->type == TOMOYO_PROFILE) { if (*line == '<') { char *cp = strchr(line, ' '); if (cp) { *cp++ = '\0'; head->w.ns = tomoyo_assign_namespace(line); memmove(line, cp, strlen(cp) + 1); } else head->w.ns = NULL; } else head->w.ns = &tomoyo_kernel_namespace; /* Don't allow updating if namespace is invalid. */ if (!head->w.ns) return -ENOENT; } /* Do the update. */ return head->write(head); } /** * tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". * @buffer: Pointer to buffer to read from. * @buffer_len: Size of @buffer. * * Returns @buffer_len on success, negative value otherwise. */ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, const char __user *buffer, const int buffer_len) { int error = buffer_len; size_t avail_len = buffer_len; char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ while (avail_len > 0) { char c; if (head->w.avail >= head->writebuf_size - 1) { const int len = head->writebuf_size * 2; char *cp = kzalloc(len, GFP_NOFS | __GFP_NOWARN); if (!cp) { error = -ENOMEM; break; } memmove(cp, cp0, head->w.avail); kfree(cp0); head->write_buf = cp; cp0 = cp; head->writebuf_size = len; } if (get_user(c, buffer)) { error = -EFAULT; break; } buffer++; avail_len--; cp0[head->w.avail++] = c; if (c != '\n') continue; cp0[head->w.avail - 1] = '\0'; head->w.avail = 0; tomoyo_normalize_line(cp0); if (!strcmp(cp0, "reset")) { head->w.ns = &tomoyo_kernel_namespace; head->w.domain = NULL; memset(&head->r, 0, sizeof(head->r)); continue; } /* Don't allow updating policies by non manager programs. */ switch (head->type) { case TOMOYO_PROCESS_STATUS: /* This does not write anything. */ break; case TOMOYO_DOMAINPOLICY: if (tomoyo_select_domain(head, cp0)) continue; fallthrough; case TOMOYO_EXCEPTIONPOLICY: if (!strcmp(cp0, "select transition_only")) { head->r.print_transition_related_only = true; continue; } fallthrough; default: if (!tomoyo_manager()) { error = -EPERM; goto out; } } switch (tomoyo_parse_policy(head, cp0)) { case -EPERM: error = -EPERM; goto out; case 0: switch (head->type) { case TOMOYO_DOMAINPOLICY: case TOMOYO_EXCEPTIONPOLICY: case TOMOYO_STAT: case TOMOYO_PROFILE: case TOMOYO_MANAGER: tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); break; default: break; } break; } } out: tomoyo_read_unlock(idx); mutex_unlock(&head->io_sem); return error; } /** * tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface. * * @head: Pointer to "struct tomoyo_io_buffer". */ void tomoyo_close_control(struct tomoyo_io_buffer *head) { /* * If the file is /sys/kernel/security/tomoyo/query , decrement the * observer counter. */ if (head->type == TOMOYO_QUERY && atomic_dec_and_test(&tomoyo_query_observers)) wake_up_all(&tomoyo_answer_wait); tomoyo_notify_gc(head, false); } /** * tomoyo_check_profile - Check all profiles currently assigned to domains are defined. */ void tomoyo_check_profile(void) { struct tomoyo_domain_info *domain; const int idx = tomoyo_read_lock(); tomoyo_policy_loaded = true; pr_info("TOMOYO: 2.6.0\n"); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { const u8 profile = domain->profile; struct tomoyo_policy_namespace *ns = domain->ns; if (ns->profile_version == 20110903) { pr_info_once("Converting profile version from %u to %u.\n", 20110903, 20150505); ns->profile_version = 20150505; } if (ns->profile_version != 20150505) pr_err("Profile version %u is not supported.\n", ns->profile_version); else if (!ns->profile_ptr[profile]) pr_err("Profile %u (used by '%s') is not defined.\n", profile, domain->domainname->name); else continue; pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n"); pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n"); panic("STOP!"); } tomoyo_read_unlock(idx); pr_info("Mandatory Access Control activated.\n"); } /** * tomoyo_load_builtin_policy - Load built-in policy. * * Returns nothing. */ void __init tomoyo_load_builtin_policy(void) { #ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING static char tomoyo_builtin_profile[] __initdata = "PROFILE_VERSION=20150505\n" "0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n"; static char tomoyo_builtin_exception_policy[] __initdata = "aggregator proc:/self/exe /proc/self/exe\n"; static char tomoyo_builtin_domain_policy[] __initdata = ""; static char tomoyo_builtin_manager[] __initdata = ""; static char tomoyo_builtin_stat[] __initdata = ""; #else /* * This include file is manually created and contains built-in policy * named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy", * "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager", * "tomoyo_builtin_stat" in the form of "static char [] __initdata". */ #include "builtin-policy.h" #endif u8 i; const int idx = tomoyo_read_lock(); for (i = 0; i < 5; i++) { struct tomoyo_io_buffer head = { }; char *start = ""; switch (i) { case 0: start = tomoyo_builtin_profile; head.type = TOMOYO_PROFILE; head.write = tomoyo_write_profile; break; case 1: start = tomoyo_builtin_exception_policy; head.type = TOMOYO_EXCEPTIONPOLICY; head.write = tomoyo_write_exception; break; case 2: start = tomoyo_builtin_domain_policy; head.type = TOMOYO_DOMAINPOLICY; head.write = tomoyo_write_domain; break; case 3: start = tomoyo_builtin_manager; head.type = TOMOYO_MANAGER; head.write = tomoyo_write_manager; break; case 4: start = tomoyo_builtin_stat; head.type = TOMOYO_STAT; head.write = tomoyo_write_stat; break; } while (1) { char *end = strchr(start, '\n'); if (!end) break; *end = '\0'; tomoyo_normalize_line(start); head.write_buf = start; tomoyo_parse_policy(&head, start); start = end + 1; } } tomoyo_read_unlock(idx); #ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER tomoyo_check_profile(); #endif } |
| 346 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H /* * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * * The use of 'struct static_key' directly, is now DEPRECATED. In addition * static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: * * struct static_key false = STATIC_KEY_INIT_FALSE; * struct static_key true = STATIC_KEY_INIT_TRUE; * static_key_true() * static_key_false() * * The updated API replacements are: * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count); * DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count); * static_branch_likely() * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we * define a "key" that is initially false via "DEFINE_STATIC_KEY_FALSE(key)", * an "if (static_branch_unlikely(&key))" statement is an unconditional branch * (which defaults to false - and the true block is placed out of line). * Similarly, we can define an initially true key via * "DEFINE_STATIC_KEY_TRUE(key)", and use it in the same * "if (static_branch_unlikely(&key))", in which case we will generate an * unconditional branch to the out-of-line true branch. Keys that are * initially true or false can be using in both static_branch_unlikely() * and static_branch_likely() statements. * * At runtime we can change the branch target by setting the key * to true via a call to static_branch_enable(), or false using * static_branch_disable(). If the direction of the branch is switched by * these calls then we run-time modify the branch target via a * no-op -> jump or jump -> no-op conversion. For example, for an * initially false key that is used in an "if (static_branch_unlikely(&key))" * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). * OTOH, since the affected branches are unconditional, their runtime overhead * will be absolutely minimal, esp. in the default (off) case where the total * effect is a single NOP of appropriate size. The on case will patch in a jump * to the out-of-line block. * * When the control is directly exposed to userspace, it is prudent to delay the * decrement to avoid high frequency code modifications which can (and do) * cause significant performance degradation. Struct static_key_deferred and * static_key_slow_dec_deferred() provide for this. * * Lacking toolchain and or architecture support, static keys fall back to a * simple conditional branch. * * Additional babbling in: Documentation/staging/static-keys.rst */ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/compiler.h> #include <linux/cleanup.h> extern bool static_key_initialized; #define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized, \ "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) struct static_key { atomic_t enabled; #ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static * initialization of them requires brackets. This creates a dependency * on the order of the struct with the initializers. If any fields * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need * to be modified. * * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod * 0 if points to struct jump_entry */ union { unsigned long type; struct jump_entry *entries; struct static_key_mod *next; }; #endif /* CONFIG_JUMP_LABEL */ }; #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL #include <asm/jump_label.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE struct jump_entry { s32 code; s32 target; long key; // key may be far away from the core kernel under KASLR }; static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return (unsigned long)&entry->code + entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return (unsigned long)&entry->target + entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } #else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; } static inline bool jump_entry_is_init(const struct jump_entry *entry) { return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry, bool set) { if (set) entry->key |= 2; else entry->key &= ~2; } static inline int jump_entry_size(struct jump_entry *entry) { #ifdef JUMP_LABEL_NOP_SIZE return JUMP_LABEL_NOP_SIZE; #else return arch_jump_entry_size(entry); #endif } #endif #endif #ifndef __ASSEMBLY__ enum jump_label_type { JUMP_LABEL_NOP = 0, JUMP_LABEL_JMP, }; struct module; #ifdef CONFIG_JUMP_LABEL #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_LINKED 2UL #define JUMP_TYPE_MASK 3UL static __always_inline bool static_key_false(struct static_key *key) { return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); extern bool static_key_slow_inc(struct static_key *key); extern bool static_key_fast_inc_not_disabled(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern bool static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); extern void static_key_enable_cpuslocked(struct static_key *key); extern void static_key_disable_cpuslocked(struct static_key *key); extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); /* * We should be using ATOMIC_INIT() for initializing .enabled, but * the inclusion of atomic.h is problematic for inclusion of jump_label.h * in 'low-level' headers. Thus, we are initializing .enabled with a * raw value, but have added a BUILD_BUG_ON() to catch any issues in * jump_label_init() see: kernel/jump_label.c. */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ #include <linux/atomic.h> #include <linux/bug.h> static __always_inline int static_key_count(struct static_key *key) { return raw_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) { static_key_initialized = true; } static __always_inline void jump_label_init_ro(void) { } static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { if (likely_notrace(static_key_count(key) > 0)) return true; return false; } static inline bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Prevent key->enabled getting negative to follow the same semantics * as for CONFIG_JUMP_LABEL=y, see kernel/jump_label.c comment. */ v = atomic_read(&key->enabled); do { if (v < 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } #define static_key_slow_inc(key) static_key_fast_inc_not_disabled(key) static inline void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); atomic_dec(&key->enabled); } #define static_key_slow_inc_cpuslocked(key) static_key_slow_inc(key) #define static_key_slow_dec_cpuslocked(key) static_key_slow_dec(key) static inline int jump_label_text_reserved(void *start, void *end) { return 0; } static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} static inline void static_key_enable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } atomic_set(&key->enabled, 0); } #define static_key_enable_cpuslocked(k) static_key_enable((k)) #define static_key_disable_cpuslocked(k) static_key_disable((k)) #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* CONFIG_JUMP_LABEL */ DEFINE_LOCK_GUARD_0(jump_label_lock, jump_label_lock(), jump_label_unlock()) #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled /* -------------------------------------------------------------------------- */ /* * Two type wrappers around static_key, such that we can use compile time * type differentiation to emit the right code. * * All the below code is macros in order to play type games. */ struct static_key_true { struct static_key key; }; struct static_key_false { struct static_key key; }; #define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } #define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT #define DEFINE_STATIC_KEY_TRUE_RO(name) \ struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT #define DEFINE_STATIC_KEY_FALSE_RO(name) \ struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name #define DEFINE_STATIC_KEY_ARRAY_TRUE(name, count) \ struct static_key_true name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_TRUE_INIT, \ } #define DEFINE_STATIC_KEY_ARRAY_FALSE(name, count) \ struct static_key_false name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \ } #define _DEFINE_STATIC_KEY_1(name) DEFINE_STATIC_KEY_TRUE(name) #define _DEFINE_STATIC_KEY_0(name) DEFINE_STATIC_KEY_FALSE(name) #define DEFINE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name) #define _DEFINE_STATIC_KEY_RO_1(name) DEFINE_STATIC_KEY_TRUE_RO(name) #define _DEFINE_STATIC_KEY_RO_0(name) DEFINE_STATIC_KEY_FALSE_RO(name) #define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name) #define _DECLARE_STATIC_KEY_1(name) DECLARE_STATIC_KEY_TRUE(name) #define _DECLARE_STATIC_KEY_0(name) DECLARE_STATIC_KEY_FALSE(name) #define DECLARE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name) extern bool ____wrong_branch_error(void); #define static_key_enabled(x) \ ({ \ if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ ____wrong_branch_error(); \ static_key_count((struct static_key *)x) > 0; \ }) #ifdef CONFIG_JUMP_LABEL /* * Combine the right initial value (type) with the right branch order * to generate the desired result. * * * type\branch| likely (1) | unlikely (0) * -----------+-----------------------+------------------ * | | * true (1) | ... | ... * | NOP | JMP L * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * | | * false (0) | ... | ... * | JMP L | NOP * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * * The initial value is encoded in the LSB of static_key::entries, * type: 0 = false, 1 = true. * * The branch type is encoded in the LSB of jump_entry::key, * branch: 0 = unlikely, 1 = likely. * * This gives the following logic table: * * enabled type branch instuction * -----------------------------+----------- * 0 0 0 | NOP * 0 0 1 | JMP * 0 1 0 | NOP * 0 1 1 | JMP * * 1 0 0 | JMP * 1 0 1 | NOP * 1 1 0 | JMP * 1 1 1 | NOP * * Which gives the following functions: * * dynamic: instruction = enabled ^ branch * static: instruction = type ^ branch * * See jump_label_type() / jump_label_init_type(). */ #define static_branch_likely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = !arch_static_branch(&(x)->key, true); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ likely_notrace(branch); \ }) #define static_branch_unlikely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = arch_static_branch_jump(&(x)->key, false); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ unlikely_notrace(branch); \ }) #else /* !CONFIG_JUMP_LABEL */ #define static_branch_likely(x) likely_notrace(static_key_enabled(&(x)->key)) #define static_branch_unlikely(x) unlikely_notrace(static_key_enabled(&(x)->key)) #endif /* CONFIG_JUMP_LABEL */ #define static_branch_maybe(config, x) \ (IS_ENABLED(config) ? static_branch_likely(x) \ : static_branch_unlikely(x)) /* * Advanced usage; refcount, branch is enabled when: count != 0 */ #define static_branch_inc(x) static_key_slow_inc(&(x)->key) #define static_branch_dec(x) static_key_slow_dec(&(x)->key) #define static_branch_inc_cpuslocked(x) static_key_slow_inc_cpuslocked(&(x)->key) #define static_branch_dec_cpuslocked(x) static_key_slow_dec_cpuslocked(&(x)->key) /* * Normal usage; boolean enable/disable. */ #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) #define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) #define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ #endif /* _LINUX_JUMP_LABEL_H */ |
| 566 538 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * VLAN An implementation of 802.1Q VLAN tagging. * * Authors: Ben Greear <greearb@candelatech.com> */ #ifndef _LINUX_IF_VLAN_H_ #define _LINUX_IF_VLAN_H_ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/bug.h> #include <uapi/linux/if_vlan.h> #define VLAN_HLEN 4 /* The additional bytes required by VLAN * (in addition to the Ethernet header) */ #define VLAN_ETH_HLEN 18 /* Total octets in header. */ #define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */ /* * According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan */ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ #define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_hdr { __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; /** * struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr) * @h_dest: destination ethernet address * @h_source: source ethernet address * @h_vlan_proto: ethernet protocol * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { struct_group(addrs, unsigned char h_dest[ETH_ALEN]; unsigned char h_source[ETH_ALEN]; ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; #include <linux/skbuff.h> static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + vlan_eth_hdr() */ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb->data; } #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); static inline bool is_vlan_dev(const struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev); } static inline int vlan_get_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev); } /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets * @tx_packets: number of transmitted packets * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters * @rx_errors: number of rx errors * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t rx_multicast; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; }; #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); /** * struct vlan_priority_tci_mapping - vlan egress priority mappings * @priority: skb priority * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 * @next: pointer to next struct */ struct vlan_priority_tci_mapping { u32 priority; u16 vlan_qos; struct vlan_priority_tci_mapping *next; }; struct proc_dir_entry; struct netpoll; /** * struct vlan_dev_priv - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings * @ingress_priority_map: ingress priority mappings * @nr_egress_mappings: number of egress priority mappings * @egress_priority_map: hash of egress priority mappings * @vlan_proto: VLAN encapsulation protocol * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats * @netpoll: netpoll instance "propagated" down to @real_dev */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; u32 ingress_priority_map[8]; unsigned int nr_egress_mappings; struct vlan_priority_tci_mapping *egress_priority_map[16]; __be16 vlan_proto; u16 vlan_id; u16 flags; struct net_device *real_dev; netdevice_tracker dev_tracker; unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; struct vlan_pcpu_stats __percpu *vlan_pcpu_stats; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) { return netdev_priv(dev); } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { struct vlan_priority_tci_mapping *mp; smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)]; while (mp) { if (mp->priority == skprio) { return mp->vlan_qos; /* This should already be shifted * to mask correctly with the * VLAN's TCI */ } mp = mp->next; } return 0; } extern bool vlan_do_receive(struct sk_buff **skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev); extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { return NULL; } static inline int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg) { return 0; } static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); return NULL; } static inline u16 vlan_dev_vlan_id(const struct net_device *dev) { BUG(); return 0; } static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) { BUG(); return 0; } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { return 0; } static inline bool vlan_do_receive(struct sk_buff **skb) { return false; } static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } static inline int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev) { return 0; } static inline void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { } static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } #endif /** * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * * Returns: true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { switch (ethertype) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) return true; return false; } /** * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Does not change skb->protocol so this function can be used during receive. * * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); /* first, the ethernet type */ if (likely(mac_len >= ETH_TLEN)) { /* h_vlan_encapsulated_proto should already be populated, and * skb->data has space for h_vlan_proto */ veth->h_vlan_proto = vlan_proto; } else { /* h_vlan_encapsulated_proto should not be populated, and * skb->data has no space for h_vlan_proto */ veth->h_vlan_encapsulated_proto = skb->protocol; } /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); return 0; } /** * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Does not change skb->protocol so this function can be used during receive. * * Returns: error if skb_cow_head fails. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { int err; err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; } return skb; } /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Return: modified @skb on success, NULL on error (@skb is freed). */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info * @skb: skbuff to clear * * Clears the VLAN information from @skb */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_all = 0; } /** * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb * @dst: skbuff to copy to * @src: skbuff to copy from * * Copies VLAN information from @src to @dst (for branchless code) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { dst->vlan_all = src->vlan_all; } /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag * * Pushes the VLAN tag from @skb->vlan_tci inside to the payload. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) { skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) __vlan_hwaccel_clear_tag(skb); return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; } /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; } /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb_vlan_tag_present(skb)) { *vlan_tci = skb_vlan_tag_get(skb); return 0; } else { *vlan_tci = 0; return -ENODATA; } } /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns: error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); } } /** * __vlan_get_protocol_offset() - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, __be16 type, int mac_offset, int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ if (eth_type_vlan(type)) { if (vlan_depth) { if (WARN_ON(vlan_depth < VLAN_HLEN)) return 0; vlan_depth -= VLAN_HLEN; } else { vlan_depth = ETH_HLEN; } do { struct vlan_hdr vhdr, *vh; vh = skb_header_pointer(skb, mac_offset + vlan_depth, sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); } if (depth) *depth = vlan_depth; return type; } static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { return __vlan_get_protocol_offset(skb, type, 0, depth); } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * * Returns: the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } /* This version of __vlan_get_protocol() also pulls mac header in skb->head */ static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, __be16 type, int *depth) { int maclen; type = __vlan_get_protocol(skb, type, &maclen); if (type) { if (!pskb_may_pull(skb, maclen)) type = 0; else if (depth) *depth = maclen; } return type; } /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) { if (!skip_vlan) /* VLAN acceleration strips the VLAN header from the skb and * moves it to skb->vlan_proto */ return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; return vlan_get_protocol(skb); } static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer * three protocols care about. */ proto = vhdr->h_vlan_encapsulated_proto; if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } rawp = (unsigned short *)(vhdr + 1); if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without * an 802.2 LLC layer. We look for FFFF which isn't a used * 802.2 SSAP/DSAP. This won't work for fault tolerant netware * but does for the rest. */ skb->protocol = htons(ETH_P_802_3); else /* * Real 802.2 LLC */ skb->protocol = htons(ETH_P_802_2); } /** * vlan_remove_tag - remove outer VLAN tag from payload * @skb: skbuff to remove tag from * @vlan_tci: buffer to store value * * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. * * Returns: a new pointer to skb->data, or NULL on failure to pull. */ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); vlan_set_encap_proto(skb, vhdr); return __skb_pull(skb, VLAN_HLEN); } /** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * * Returns: true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) { if (!skb_vlan_tag_present(skb) && likely(!eth_type_vlan(skb->protocol))) return false; return true; } /** * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * * Returns: true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; if (!skb_vlan_tag_present(skb)) { struct vlan_ethhdr *veh; if (likely(!eth_type_vlan(protocol))) return false; if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } if (!eth_type_vlan(protocol)) return false; return true; } /** * vlan_features_check - drop unsafe features for skb with multiple tags. * @skb: skbuff to query * @features: features to be checked * * Returns: features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { /* In the case of multi-tagged packets, use a direct mask * instead of using netdev_interesect_features(), to make * sure that only devices supporting NETIF_F_HW_CSUM will * have checksum offloading support. */ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } return features; } /** * compare_vlan_header - Compare two vlan headers * @h1: Pointer to vlan header * @h2: Pointer to vlan header * * Compare two vlan headers. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. * * Return: 0 if equal, arbitrary non-zero value if not equal. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return *(u32 *)h1 ^ *(u32 *)h2; #else return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | ((__force u32)h1->h_vlan_encapsulated_proto ^ (__force u32)h2->h_vlan_encapsulated_proto); #endif } #endif /* !(_LINUX_IF_VLAN_H_) */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.pf != NFPROTO_NETDEV || hook->ops.hooknum != NF_NETDEV_INGRESS) return false; dev = hook->ops.dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct net_device *dev; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { dev = hook->ops.dev; if (this_dev && this_dev != dev) continue; err = nft_chain_offload_cmd(basechain, dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { if (i-- <= 0) break; dev = hook->ops.dev; nft_chain_offload_cmd(basechain, dev, FLOW_BLOCK_UNBIND); } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->flags & NLM_F_REPLACE || !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 1 967 29 22 48 930 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> #include <linux/cleanup.h> #include <linux/err.h> struct file; extern void fput(struct file *); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); /* either a reference to struct file + flags * (cloned vs. borrowed, pos locked), with * flags stored in lower bits of value, * or empty (represented by 0). */ struct fd { unsigned long word; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 #define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK))) static inline bool fd_empty(struct fd f) { return unlikely(!f.word); } #define EMPTY_FD (struct fd){0} static inline struct fd BORROWED_FD(struct file *f) { return (struct fd){(unsigned long)f}; } static inline struct fd CLONED_FD(struct file *f) { return (struct fd){(unsigned long)f | FDPUT_FPUT}; } static inline void fdput(struct fd fd) { if (fd.word & FDPUT_FPUT) fput(fd_file(fd)); } extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); extern void __f_unlock_pos(struct file *); struct fd fdget(unsigned int fd); struct fd fdget_raw(unsigned int fd); struct fd fdget_pos(unsigned int fd); static inline void fdput_pos(struct fd f) { if (f.word & FDPUT_POS_UNLOCK) __f_unlock_pos(fd_file(f)); fdput(f); } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T)) /* * take_fd() will take care to set @fd to -EBADF ensuring that * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it * easier to rely on CLASS(get_unused_fd): * * struct file *f; * * CLASS(get_unused_fd, fd)(O_CLOEXEC); * if (fd < 0) * return fd; * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); */ #define take_fd(fd) __get_and_null(fd, -EBADF) extern void fd_install(unsigned int fd, struct file *file); int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags); extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; #endif /* __LINUX_FILE_H */ |
| 416 534 380 381 199 198 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ bool lockref_get_not_zero(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count > 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return false; lockref->count--; spin_unlock(&lockref->lock); return true; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ bool lockref_get_not_dead(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count >= 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 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 | #include <linux/init.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/net_namespace.h> #include <net/netfilter/nf_tables.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter_arp.h> #include <net/netfilter/nf_tables_ipv4.h> #include <net/netfilter/nf_tables_ipv6.h> #ifdef CONFIG_NF_TABLES_IPV4 static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); nft_set_pktinfo_ipv4(&pkt); return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_ipv4 = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_IPV4, .hook_mask = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_LOCAL_IN] = nft_do_chain_ipv4, [NF_INET_LOCAL_OUT] = nft_do_chain_ipv4, [NF_INET_FORWARD] = nft_do_chain_ipv4, [NF_INET_PRE_ROUTING] = nft_do_chain_ipv4, [NF_INET_POST_ROUTING] = nft_do_chain_ipv4, }, }; static void nft_chain_filter_ipv4_init(void) { nft_register_chain_type(&nft_chain_filter_ipv4); } static void nft_chain_filter_ipv4_fini(void) { nft_unregister_chain_type(&nft_chain_filter_ipv4); } #else static inline void nft_chain_filter_ipv4_init(void) {} static inline void nft_chain_filter_ipv4_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV4 */ #ifdef CONFIG_NF_TABLES_ARP static unsigned int nft_do_chain_arp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); nft_set_pktinfo_unspec(&pkt); return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_arp = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_ARP, .owner = THIS_MODULE, .hook_mask = (1 << NF_ARP_IN) | (1 << NF_ARP_OUT), .hooks = { [NF_ARP_IN] = nft_do_chain_arp, [NF_ARP_OUT] = nft_do_chain_arp, }, }; static void nft_chain_filter_arp_init(void) { nft_register_chain_type(&nft_chain_filter_arp); } static void nft_chain_filter_arp_fini(void) { nft_unregister_chain_type(&nft_chain_filter_arp); } #else static inline void nft_chain_filter_arp_init(void) {} static inline void nft_chain_filter_arp_fini(void) {} #endif /* CONFIG_NF_TABLES_ARP */ #ifdef CONFIG_NF_TABLES_IPV6 static unsigned int nft_do_chain_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); nft_set_pktinfo_ipv6(&pkt); return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_ipv6 = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_IPV6, .hook_mask = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_LOCAL_IN] = nft_do_chain_ipv6, [NF_INET_LOCAL_OUT] = nft_do_chain_ipv6, [NF_INET_FORWARD] = nft_do_chain_ipv6, [NF_INET_PRE_ROUTING] = nft_do_chain_ipv6, [NF_INET_POST_ROUTING] = nft_do_chain_ipv6, }, }; static void nft_chain_filter_ipv6_init(void) { nft_register_chain_type(&nft_chain_filter_ipv6); } static void nft_chain_filter_ipv6_fini(void) { nft_unregister_chain_type(&nft_chain_filter_ipv6); } #else static inline void nft_chain_filter_ipv6_init(void) {} static inline void nft_chain_filter_ipv6_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ #ifdef CONFIG_NF_TABLES_INET static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (state->pf) { case NFPROTO_IPV4: nft_set_pktinfo_ipv4(&pkt); break; case NFPROTO_IPV6: nft_set_pktinfo_ipv6(&pkt); break; default: break; } return nft_do_chain(&pkt, priv); } static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_hook_state ingress_state = *state; struct nft_pktinfo pkt; switch (skb->protocol) { case htons(ETH_P_IP): /* Original hook is NFPROTO_NETDEV and NF_NETDEV_INGRESS. */ ingress_state.pf = NFPROTO_IPV4; ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); if (nft_set_pktinfo_ipv4_ingress(&pkt) < 0) return NF_DROP; break; case htons(ETH_P_IPV6): ingress_state.pf = NFPROTO_IPV6; ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); if (nft_set_pktinfo_ipv6_ingress(&pkt) < 0) return NF_DROP; break; default: return NF_ACCEPT; } return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_inet = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_INET, .hook_mask = (1 << NF_INET_INGRESS) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_INGRESS] = nft_do_chain_inet_ingress, [NF_INET_LOCAL_IN] = nft_do_chain_inet, [NF_INET_LOCAL_OUT] = nft_do_chain_inet, [NF_INET_FORWARD] = nft_do_chain_inet, [NF_INET_PRE_ROUTING] = nft_do_chain_inet, [NF_INET_POST_ROUTING] = nft_do_chain_inet, }, }; static void nft_chain_filter_inet_init(void) { nft_register_chain_type(&nft_chain_filter_inet); } static void nft_chain_filter_inet_fini(void) { nft_unregister_chain_type(&nft_chain_filter_inet); } #else static inline void nft_chain_filter_inet_init(void) {} static inline void nft_chain_filter_inet_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ #if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) static unsigned int nft_do_chain_bridge(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): nft_set_pktinfo_ipv6_validate(&pkt); break; default: nft_set_pktinfo_unspec(&pkt); break; } return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_bridge = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_BRIDGE, .hook_mask = (1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | (1 << NF_BR_LOCAL_OUT) | (1 << NF_BR_POST_ROUTING), .hooks = { [NF_BR_PRE_ROUTING] = nft_do_chain_bridge, [NF_BR_LOCAL_IN] = nft_do_chain_bridge, [NF_BR_FORWARD] = nft_do_chain_bridge, [NF_BR_LOCAL_OUT] = nft_do_chain_bridge, [NF_BR_POST_ROUTING] = nft_do_chain_bridge, }, }; static void nft_chain_filter_bridge_init(void) { nft_register_chain_type(&nft_chain_filter_bridge); } static void nft_chain_filter_bridge_fini(void) { nft_unregister_chain_type(&nft_chain_filter_bridge); } #else static inline void nft_chain_filter_bridge_init(void) {} static inline void nft_chain_filter_bridge_fini(void) {} #endif /* CONFIG_NF_TABLES_BRIDGE */ #ifdef CONFIG_NF_TABLES_NETDEV static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (skb->protocol) { case htons(ETH_P_IP): nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): nft_set_pktinfo_ipv6_validate(&pkt); break; default: nft_set_pktinfo_unspec(&pkt); break; } return nft_do_chain(&pkt, priv); } static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, .hook_mask = (1 << NF_NETDEV_INGRESS) | (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; static void nft_netdev_event(unsigned long event, struct net_device *dev, struct nft_base_chain *basechain) { struct nft_hook *hook; list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev != dev) continue; if (!(basechain->chain.table->flags & NFT_TABLE_F_DORMANT)) nf_unregister_net_hook(dev_net(dev), &hook->ops); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); break; } } static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_base_chain *basechain; struct nftables_pernet *nft_net; struct nft_chain *chain; struct nft_table *table; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(dev_net(dev)); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV && table->family != NFPROTO_INET) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain)) continue; basechain = nft_base_chain(chain); if (table->family == NFPROTO_INET && basechain->ops.hooknum != NF_INET_INGRESS) continue; nft_netdev_event(event, dev, basechain); } } mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nf_tables_netdev_notifier = { .notifier_call = nf_tables_netdev_event, }; static int nft_chain_filter_netdev_init(void) { int err; nft_register_chain_type(&nft_chain_filter_netdev); err = register_netdevice_notifier(&nf_tables_netdev_notifier); if (err) goto err_register_netdevice_notifier; return 0; err_register_netdevice_notifier: nft_unregister_chain_type(&nft_chain_filter_netdev); return err; } static void nft_chain_filter_netdev_fini(void) { nft_unregister_chain_type(&nft_chain_filter_netdev); unregister_netdevice_notifier(&nf_tables_netdev_notifier); } #else static inline int nft_chain_filter_netdev_init(void) { return 0; } static inline void nft_chain_filter_netdev_fini(void) {} #endif /* CONFIG_NF_TABLES_NETDEV */ int __init nft_chain_filter_init(void) { int err; err = nft_chain_filter_netdev_init(); if (err < 0) return err; nft_chain_filter_ipv4_init(); nft_chain_filter_ipv6_init(); nft_chain_filter_arp_init(); nft_chain_filter_inet_init(); nft_chain_filter_bridge_init(); return 0; } void nft_chain_filter_fini(void) { nft_chain_filter_bridge_fini(); nft_chain_filter_inet_fini(); nft_chain_filter_arp_fini(); nft_chain_filter_ipv6_fini(); nft_chain_filter_ipv4_fini(); nft_chain_filter_netdev_fini(); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master, int extra) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; int len; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; len = sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload); /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header. * RedBox might use @extra more bytes. */ skb = dev_alloc_skb(len + extra + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; skb_reset_network_header(skb); skb_reset_transport_header(skb); 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); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; int extra = 0; *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++; } if (hsr->redbox) extra = sizeof(struct hsr_sup_tlv) + sizeof(struct hsr_sup_payload); skb = hsr_init_skb(port, extra); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master, 0); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: 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 int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { bool is_slave_a_added = false; bool is_slave_b_added = false; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; ret = vlan_vid_add(port->dev, proto, vid); switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); if (is_slave_b_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_a_added = true; break; case HSR_PT_SLAVE_B: if (ret) { /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); if (is_slave_a_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_b_added = true; break; default: break; } } return 0; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: vlan_vid_del(port->dev, proto, vid); break; default: break; } } return 0; } 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, .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; 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; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_local = true; 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 | NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; } /* 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); struct net_device *hsr_get_port_ndev(struct net_device *ndev, enum hsr_port_type pt) { struct hsr_priv *hsr = netdev_priv(ndev); struct hsr_port *port; hsr_for_each_port(hsr, port) if (port->type == pt) return port->dev; return NULL; } EXPORT_SYMBOL(hsr_get_port_ndev); /* 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; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; 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; } |
| 89 524 369 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 198 199 2 198 199 182 2 2 2 2 182 2 215 1 181 216 215 216 216 215 45 198 199 2 2 2 45 45 45 5 5 5 45 45 45 5 45 5 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" #include "services.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[] __counted_by(len); }; #define index_to_sid(index) ((index) + SECINITSID_NUM + 1) #define sid_to_index(sid) ((sid) - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_equal(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { unsigned int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; unsigned int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc( SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ convert = s->convert; if (convert) { struct sidtab *target = convert->target; rc = -ENOMEM; dst_convert = sidtab_do_lookup(target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = services_convert_context(convert->args, context, &dst_convert->context, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); target->count = count + 1; hash_add_rcu(target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = services_convert_context( convert->args, &esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, GFP_KERNEL); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(struct_size(cache, str, str_len), GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 253 64 65 136 253 57 219 252 252 253 253 219 136 219 220 136 136 219 188 142 220 220 57 220 220 220 138 136 136 136 136 136 220 220 57 57 57 138 138 38 38 268 20 343 344 404 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs, bool workingset) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment on MAX_NR_TIERS */ return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); if (!(flags & BIT(PG_referenced))) return 0; /* * Return the total number of accesses including PG_referenced. Also see * the comment on LRU_REFS_FLAGS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1; } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; /* * +-----------------------------------+-----------------------------------+ * | Accessed through page tables and | Accessed through file descriptors | * | promoted by folio_update_gen() | and protected by folio_inc_gen() | * +-----------------------------------+-----------------------------------+ * | PG_active (set while isolated) | | * +-----------------+-----------------+-----------------+-----------------+ * | PG_workingset | PG_referenced | PG_workingset | LRU_REFS_FLAGS | * +-----------------------------------+-----------------------------------+ * |<---------- MIN_NR_GENS ---------->| | * |<---------------------------- MAX_NR_GENS ---------------------------->| */ if (folio_test_active(folio)) gen = MIN_NR_GENS - folio_test_workingset(folio); else if (reclaiming) gen = MAX_NR_GENS; else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) gen = MIN_NR_GENS; else gen = MAX_NR_GENS - folio_test_workingset(folio); return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type])); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; seq = lru_gen_folio_seq(lruvec, folio, reclaiming); gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; set_mask_bits(&new->flags, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * Returns true if an uffd-wp pte was installed, false otherwise. */ static inline bool pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return false; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); return true; } #endif return false; } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 | /* * linux/include/linux/console.h * * Copyright (C) 1993 Hamish Macdonald * * 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. * * Changed: * 10-Mar-94: Arno Griffioen: Conversion for vt100 emulator port from PC LINUX */ #ifndef _LINUX_CONSOLE_H_ #define _LINUX_CONSOLE_H_ 1 #include <linux/atomic.h> #include <linux/bits.h> #include <linux/irq_work.h> #include <linux/rculist.h> #include <linux/rcuwait.h> #include <linux/types.h> #include <linux/vesa.h> struct vc_data; struct console_font_op; struct console_font; struct module; struct tty_struct; struct notifier_block; enum con_scroll { SM_UP, SM_DOWN, }; enum vc_intensity; /** * struct consw - callbacks for consoles * * @owner: the module to get references of when this console is used * @con_startup: set up the console and return its name (like VGA, EGA, ...) * @con_init: initialize the console on @vc. @init is true for the very first * call on this @vc. * @con_deinit: deinitialize the console from @vc. * @con_clear: erase @count characters at [@x, @y] on @vc. @count >= 1. * @con_putc: emit one character with attributes @ca to [@x, @y] on @vc. * (optional -- @con_putcs would be called instead) * @con_putcs: emit @count characters with attributes @s to [@x, @y] on @vc. * @con_cursor: enable/disable cursor depending on @enable * @con_scroll: move lines from @top to @bottom in direction @dir by @lines. * Return true if no generic handling should be done. * Invoked by csi_M and printing to the console. * @con_switch: notifier about the console switch; it is supposed to return * true if a redraw is needed. * @con_blank: blank/unblank the console. The target mode is passed in @blank. * @mode_switch is set if changing from/to text/graphics. The hook * is supposed to return true if a redraw is needed. * @con_font_set: set console @vc font to @font with height @vpitch. @flags can * be %KD_FONT_FLAG_DONT_RECALC. (optional) * @con_font_get: fetch the current font on @vc of height @vpitch into @font. * (optional) * @con_font_default: set default font on @vc. @name can be %NULL or font name * to search for. @font can be filled back. (optional) * @con_resize: resize the @vc console to @width x @height. @from_user is true * when this change comes from the user space. * @con_set_palette: sets the palette of the console @vc to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) * @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not * provided or returns false, the origin is set to * @vc->vc_screenbuf. (optional) * @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g. * upon entering graphics. (optional) * @con_build_attr: build attributes based on @color, @intensity and other * parameters. The result is used for both normal and erase * characters. (optional) * @con_invert_region: invert a region of length @count on @vc starting at @p. * (optional) * @con_debug_enter: prepare the console for the debugger. This includes, but * is not limited to, unblanking the console, loading an * appropriate palette, and allowing debugger generated output. * (optional) * @con_debug_leave: restore the console to its pre-debug state as closely as * possible. (optional) */ struct consw { struct module *owner; const char *(*con_startup)(void); void (*con_init)(struct vc_data *vc, bool init); void (*con_deinit)(struct vc_data *vc); void (*con_clear)(struct vc_data *vc, unsigned int y, unsigned int x, unsigned int count); void (*con_putc)(struct vc_data *vc, u16 ca, unsigned int y, unsigned int x); void (*con_putcs)(struct vc_data *vc, const u16 *s, unsigned int count, unsigned int ypos, unsigned int xpos); void (*con_cursor)(struct vc_data *vc, bool enable); bool (*con_scroll)(struct vc_data *vc, unsigned int top, unsigned int bottom, enum con_scroll dir, unsigned int lines); bool (*con_switch)(struct vc_data *vc); bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank, bool mode_switch); int (*con_font_set)(struct vc_data *vc, const struct console_font *font, unsigned int vpitch, unsigned int flags); int (*con_font_get)(struct vc_data *vc, struct console_font *font, unsigned int vpitch); int (*con_font_default)(struct vc_data *vc, struct console_font *font, const char *name); int (*con_resize)(struct vc_data *vc, unsigned int width, unsigned int height, bool from_user); void (*con_set_palette)(struct vc_data *vc, const unsigned char *table); void (*con_scrolldelta)(struct vc_data *vc, int lines); bool (*con_set_origin)(struct vc_data *vc); void (*con_save_screen)(struct vc_data *vc); u8 (*con_build_attr)(struct vc_data *vc, u8 color, enum vc_intensity intensity, bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); void (*con_debug_enter)(struct vc_data *vc); void (*con_debug_leave)(struct vc_data *vc); }; extern const struct consw *conswitchp; extern const struct consw dummy_con; /* dummy console buffer */ extern const struct consw vga_con; /* VGA text console */ extern const struct consw newport_con; /* SGI Newport console */ struct screen_info; #ifdef CONFIG_VGA_CONSOLE void vgacon_register_screen(struct screen_info *si); #else static inline void vgacon_register_screen(struct screen_info *si) { } #endif int con_is_bound(const struct consw *csw); int do_unregister_con_driver(const struct consw *csw); int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); #ifdef CONFIG_VT void con_debug_enter(struct vc_data *vc); void con_debug_leave(void); #else static inline void con_debug_enter(struct vc_data *vc) { } static inline void con_debug_leave(void) { } #endif /* * The interface for a console, or any other device that wants to capture * console messages (printer driver?) */ /** * enum cons_flags - General console flags * @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate * output of messages that were already shown by boot * consoles or read by userspace via syslog() syscall. * @CON_CONSDEV: Indicates that the console driver is backing * /dev/console. * @CON_ENABLED: Indicates if a console is allowed to print records. If * false, the console also will not advance to later * records. * @CON_BOOT: Marks the console driver as early console driver which * is used during boot before the real driver becomes * available. It will be automatically unregistered * when the real console driver is registered unless * "keep_bootcon" parameter is used. * @CON_ANYTIME: A misnomed historical flag which tells the core code * that the legacy @console::write callback can be invoked * on a CPU which is marked OFFLINE. That is misleading as * it suggests that there is no contextual limit for * invoking the callback. The original motivation was * readiness of the per-CPU areas. * @CON_BRL: Indicates a braille device which is exempt from * receiving the printk spam for obvious reasons. * @CON_EXTENDED: The console supports the extended output format of * /dev/kmesg which requires a larger output buffer. * @CON_SUSPENDED: Indicates if a console is suspended. If true, the * printing callbacks must not be called. * @CON_NBCON: Console can operate outside of the legacy style console_lock * constraints. */ enum cons_flags { CON_PRINTBUFFER = BIT(0), CON_CONSDEV = BIT(1), CON_ENABLED = BIT(2), CON_BOOT = BIT(3), CON_ANYTIME = BIT(4), CON_BRL = BIT(5), CON_EXTENDED = BIT(6), CON_SUSPENDED = BIT(7), CON_NBCON = BIT(8), }; /** * struct nbcon_state - console state for nbcon consoles * @atom: Compound of the state fields for atomic operations * * @req_prio: The priority of a handover request * @prio: The priority of the current owner * @unsafe: Console is busy in a non takeover region * @unsafe_takeover: A hostile takeover in an unsafe state happened in the * past. The console cannot be safe until re-initialized. * @cpu: The CPU on which the owner runs * * To be used for reading and preparing of the value stored in the nbcon * state variable @console::nbcon_state. * * The @prio and @req_prio fields are particularly important to allow * spin-waiting to timeout and give up without the risk of a waiter being * assigned the lock after giving up. */ struct nbcon_state { union { unsigned int atom; struct { unsigned int prio : 2; unsigned int req_prio : 2; unsigned int unsafe : 1; unsigned int unsafe_takeover : 1; unsigned int cpu : 24; }; }; }; /* * The nbcon_state struct is used to easily create and interpret values that * are stored in the @console::nbcon_state variable. Ensure this struct stays * within the size boundaries of the atomic variable's underlying type in * order to avoid any accidental truncation. */ static_assert(sizeof(struct nbcon_state) <= sizeof(int)); /** * enum nbcon_prio - console owner priority for nbcon consoles * @NBCON_PRIO_NONE: Unused * @NBCON_PRIO_NORMAL: Normal (non-emergency) usage * @NBCON_PRIO_EMERGENCY: Emergency output (WARN/OOPS...) * @NBCON_PRIO_PANIC: Panic output * @NBCON_PRIO_MAX: The number of priority levels * * A higher priority context can takeover the console when it is * in the safe state. The final attempt to flush consoles in panic() * can be allowed to do so even in an unsafe state (Hope and pray). */ enum nbcon_prio { NBCON_PRIO_NONE = 0, NBCON_PRIO_NORMAL, NBCON_PRIO_EMERGENCY, NBCON_PRIO_PANIC, NBCON_PRIO_MAX, }; struct console; struct printk_buffers; /** * struct nbcon_context - Context for console acquire/release * @console: The associated console * @spinwait_max_us: Limit for spin-wait acquire * @prio: Priority of the context * @allow_unsafe_takeover: Allow performing takeover even if unsafe. Can * be used only with NBCON_PRIO_PANIC @prio. It * might cause a system freeze when the console * is used later. * @backlog: Ringbuffer has pending records * @pbufs: Pointer to the text buffer for this context * @seq: The sequence number to print for this context */ struct nbcon_context { /* members set by caller */ struct console *console; unsigned int spinwait_max_us; enum nbcon_prio prio; unsigned int allow_unsafe_takeover : 1; /* members set by emit */ unsigned int backlog : 1; /* members set by acquire */ struct printk_buffers *pbufs; u64 seq; }; /** * struct nbcon_write_context - Context handed to the nbcon write callbacks * @ctxt: The core console context * @outbuf: Pointer to the text buffer for output * @len: Length to write * @unsafe_takeover: If a hostile takeover in an unsafe state has occurred */ struct nbcon_write_context { struct nbcon_context __private ctxt; char *outbuf; unsigned int len; bool unsafe_takeover; }; /** * struct console - The console descriptor structure * @name: The name of the console driver * @write: Legacy write callback to output messages (Optional) * @read: Read callback for console input (Optional) * @device: The underlying TTY device driver (Optional) * @unblank: Callback to unblank the console (Optional) * @setup: Callback for initializing the console (Optional) * @exit: Callback for teardown of the console (Optional) * @match: Callback for matching a console (Optional) * @flags: Console flags. See enum cons_flags * @index: Console index, e.g. port number * @cflag: TTY control mode flags * @ispeed: TTY input speed * @ospeed: TTY output speed * @seq: Sequence number of the next ringbuffer record to print * @dropped: Number of unreported dropped ringbuffer records * @data: Driver private data * @node: hlist node for the console list * * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print * @nbcon_device_ctxt: Context available for non-printing operations * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer * @kthread: Printer kthread for this console * @rcuwait: RCU-safe wait object for @kthread waking * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; void (*write)(struct console *co, const char *s, unsigned int count); int (*read)(struct console *co, char *s, unsigned int count); struct tty_driver *(*device)(struct console *co, int *index); void (*unblank)(void); int (*setup)(struct console *co, char *options); int (*exit)(struct console *co); int (*match)(struct console *co, char *name, int idx, char *options); short flags; short index; int cflag; uint ispeed; uint ospeed; u64 seq; unsigned long dropped; void *data; struct hlist_node node; /* nbcon console specific members */ /** * @write_atomic: * * NBCON callback to write out text in any context. (Optional) * * This callback is called with the console already acquired. However, * a higher priority context is allowed to take it over by default. * * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() * around any code where the takeover is not safe, for example, when * manipulating the serial port registers. * * nbcon_enter_unsafe() will fail if the context has lost the console * ownership in the meantime. In this case, the callback is no longer * allowed to go forward. It must back out immediately and carefully. * The buffer content is also no longer trusted since it no longer * belongs to the context. * * The callback should allow the takeover whenever it is safe. It * increases the chance to see messages when the system is in trouble. * If the driver must reacquire ownership in order to finalize or * revert hardware changes, nbcon_reacquire_nobuf() can be used. * However, on reacquire the buffer content is no longer available. A * reacquire cannot be used to resume printing. * * The callback can be called from any context (including NMI). * Therefore it must avoid usage of any locking and instead rely * on the console ownership for synchronization. */ void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); /** * @write_thread: * * NBCON callback to write out text in task context. * * This callback must be called only in task context with both * device_lock() and the nbcon console acquired with * NBCON_PRIO_NORMAL. * * The same rules for console ownership verification and unsafe * sections handling applies as with write_atomic(). * * The console ownership handling is necessary for synchronization * against write_atomic() which is synchronized only via the context. * * The device_lock() provides the primary serialization for operations * on the device. It might be as relaxed (mutex)[*] or as tight * (disabled preemption and interrupts) as needed. It allows * the kthread to operate in the least restrictive mode[**]. * * [*] Standalone nbcon_context_try_acquire() is not safe with * the preemption enabled, see nbcon_owner_matches(). But it * can be safe when always called in the preemptive context * under the device_lock(). * * [**] The device_lock() makes sure that nbcon_context_try_acquire() * would never need to spin which is important especially with * PREEMPT_RT. */ void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); /** * @device_lock: * * NBCON callback to begin synchronization with driver code. * * Console drivers typically must deal with access to the hardware * via user input/output (such as an interactive login shell) and * output of kernel messages via printk() calls. This callback is * called by the printk-subsystem whenever it needs to synchronize * with hardware access by the driver. It should be implemented to * use whatever synchronization mechanism the driver is using for * itself (for example, the port lock for uart serial consoles). * * The callback is always called from task context. It may use any * synchronization method required by the driver. * * IMPORTANT: The callback MUST disable migration. The console driver * may be using a synchronization mechanism that already takes * care of this (such as spinlocks). Otherwise this function must * explicitly call migrate_disable(). * * The flags argument is provided as a convenience to the driver. It * will be passed again to device_unlock(). It can be ignored if the * driver does not need it. */ void (*device_lock)(struct console *con, unsigned long *flags); /** * @device_unlock: * * NBCON callback to finish synchronization with driver code. * * It is the counterpart to device_lock(). * * This callback is always called from task context. It must * appropriately re-enable migration (depending on how device_lock() * disabled migration). * * The flags argument is the value of the same variable that was * passed to device_lock(). */ void (*device_unlock)(struct console *con, unsigned long flags); atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct nbcon_context __private nbcon_device_ctxt; atomic_long_t __private nbcon_prev_seq; struct printk_buffers *pbufs; struct task_struct *kthread; struct rcuwait rcuwait; struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP extern void lockdep_assert_console_list_lock_held(void); #else static inline void lockdep_assert_console_list_lock_held(void) { } #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC extern bool console_srcu_read_lock_is_held(void); #else static inline bool console_srcu_read_lock_is_held(void) { return 1; } #endif extern int console_srcu_read_lock(void); extern void console_srcu_read_unlock(int cookie); extern void console_list_lock(void) __acquires(console_mutex); extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; /** * console_srcu_read_flags - Locklessly read flags of a possibly registered * console * @con: struct console pointer of console to read flags from * * Locklessly reading @con->flags provides a consistent read value because * there is at most one CPU modifying @con->flags and that CPU is using only * read-modify-write operations to do so. * * Requires console_srcu_read_lock to be held, which implies that @con might * be a registered console. The purpose of holding console_srcu_read_lock is * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) * and that no exit/cleanup routines will run if the console is currently * undergoing unregistration. * * If the caller is holding the console_list_lock or it is _certain_ that * @con is not and will not become registered, the caller may read * @con->flags directly instead. * * Context: Any context. * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } /** * console_srcu_write_flags - Write flags for a registered console * @con: struct console pointer of console to write flags to * @flags: new flags value to write * * Only use this function to write flags for registered consoles. It * requires holding the console_list_lock. * * Context: Any context. */ static inline void console_srcu_write_flags(struct console *con, short flags) { lockdep_assert_console_list_lock_held(); /* This matches the READ_ONCE() in console_srcu_read_flags(). */ WRITE_ONCE(con->flags, flags); } /* Variant of console_is_registered() when the console_list_lock is held. */ static inline bool console_is_registered_locked(const struct console *con) { lockdep_assert_console_list_lock_held(); return !hlist_unhashed(&con->node); } /* * console_is_registered - Check if the console is registered * @con: struct console pointer of console to check * * Context: Process context. May sleep while acquiring console list lock. * Return: true if the console is in the console list, otherwise false. * * If false is returned for a console that was previously registered, it * can be assumed that the console's unregistration is fully completed, * including the exit() callback after console list removal. */ static inline bool console_is_registered(const struct console *con) { bool ret; console_list_lock(); ret = console_is_registered_locked(con); console_list_unlock(); return ret; } /** * for_each_console_srcu() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * Although SRCU guarantees the console list will be consistent, the * struct console fields may be updated by other CPUs while iterating. * * Requires console_srcu_read_lock to be held. Can be invoked from * any context. */ #define for_each_console_srcu(con) \ hlist_for_each_entry_srcu(con, &console_list, node, \ console_srcu_read_lock_is_held()) /** * for_each_console() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * The console list and the &console.flags are immutable while iterating. * * Requires console_list_lock to be held. */ #define for_each_console(con) \ lockdep_assert_console_list_lock_held(); \ hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK extern void nbcon_cpu_emergency_enter(void); extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); #else static inline void nbcon_cpu_emergency_enter(void) { } static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } #endif extern int console_set_on_cmdline; extern struct console *early_console; enum con_flush_mode { CONSOLE_FLUSH_PENDING, CONSOLE_REPLAY_ALL, }; extern int add_preferred_console(const char *name, const short idx, char *options); extern void console_force_preferred_locked(struct console *con); extern void register_console(struct console *); extern int unregister_console(struct console *); extern void console_lock(void); extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); extern void console_flush_on_panic(enum con_flush_mode mode); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); extern int is_console_locked(void); extern int braille_register_console(struct console *, int index, char *console_options, char *braille_options); extern int braille_unregister_console(struct console *); #ifdef CONFIG_TTY extern void console_sysfs_notify(void); #else static inline void console_sysfs_notify(void) { } #endif extern bool console_suspend_enabled; /* Suspend and resume console messages over PM events */ extern void suspend_console(void); extern void resume_console(void); int mda_console_init(void); void vcs_make_sysfs(int index); void vcs_remove_sysfs(int index); /* Some debug stub to catch some of the obvious races in the VT code */ #define WARN_CONSOLE_UNLOCKED() \ WARN_ON(!atomic_read(&ignore_console_lock_warning) && \ !is_console_locked() && !oops_in_progress) /* * Increment ignore_console_lock_warning if you need to quiet * WARN_CONSOLE_UNLOCKED() for debugging purposes. */ extern atomic_t ignore_console_lock_warning; extern void console_init(void); /* For deferred console takeover */ void dummycon_register_output_notifier(struct notifier_block *nb); void dummycon_unregister_output_notifier(struct notifier_block *nb); #endif /* _LINUX_CONSOLE_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/if.h> #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/sch_generic.h> #include <linux/netfilter.h> #include <rdma/ib_addr.h> #include "rxe.h" #include "rxe_net.h" #include "rxe_loc.h" static struct rxe_recv_sockets recv_sockets; static struct dst_entry *rxe_find_route4(struct rxe_qp *qp, struct net_device *ndev, struct in_addr *saddr, struct in_addr *daddr) { struct rtable *rt; struct flowi4 fl = { { 0 } }; memset(&fl, 0, sizeof(fl)); fl.flowi4_oif = ndev->ifindex; memcpy(&fl.saddr, saddr, sizeof(*saddr)); memcpy(&fl.daddr, daddr, sizeof(*daddr)); fl.flowi4_proto = IPPROTO_UDP; rt = ip_route_output_key(&init_net, &fl); if (IS_ERR(rt)) { rxe_dbg_qp(qp, "no route to %pI4\n", &daddr->s_addr); return NULL; } return &rt->dst; } #if IS_ENABLED(CONFIG_IPV6) static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { struct dst_entry *ndst; struct flowi6 fl6 = { { 0 } }; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = ndev->ifindex; memcpy(&fl6.saddr, saddr, sizeof(*saddr)); memcpy(&fl6.daddr, daddr, sizeof(*daddr)); fl6.flowi6_proto = IPPROTO_UDP; ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk), recv_sockets.sk6->sk, &fl6, NULL); if (IS_ERR(ndst)) { rxe_dbg_qp(qp, "no route to %pI6\n", daddr); return NULL; } if (unlikely(ndst->error)) { rxe_dbg_qp(qp, "no route to %pI6\n", daddr); goto put; } return ndst; put: dst_release(ndst); return NULL; } #else static struct dst_entry *rxe_find_route6(struct rxe_qp *qp, struct net_device *ndev, struct in6_addr *saddr, struct in6_addr *daddr) { return NULL; } #endif static struct dst_entry *rxe_find_route(struct net_device *ndev, struct rxe_qp *qp, struct rxe_av *av) { struct dst_entry *dst = NULL; if (qp_type(qp) == IB_QPT_RC) dst = sk_dst_get(qp->sk->sk); if (!dst || !dst_check(dst, qp->dst_cookie)) { if (dst) dst_release(dst); if (av->network_type == RXE_NETWORK_TYPE_IPV4) { struct in_addr *saddr; struct in_addr *daddr; saddr = &av->sgid_addr._sockaddr_in.sin_addr; daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route4(qp, ndev, saddr, daddr); } else if (av->network_type == RXE_NETWORK_TYPE_IPV6) { struct in6_addr *saddr6; struct in6_addr *daddr6; saddr6 = &av->sgid_addr._sockaddr_in6.sin6_addr; daddr6 = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route6(qp, ndev, saddr6, daddr6); #if IS_ENABLED(CONFIG_IPV6) if (dst) qp->dst_cookie = rt6_get_cookie((struct rt6_info *)dst); #endif } if (dst && (qp_type(qp) == IB_QPT_RC)) { dst_hold(dst); sk_dst_set(qp->sk->sk, dst); } } return dst; } static int rxe_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct udphdr *udph; struct rxe_dev *rxe; struct net_device *ndev = skb->dev; struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); /* takes a reference on rxe->ib_dev * drop when skb is freed */ rxe = rxe_get_dev_from_net(ndev); if (!rxe && is_vlan_dev(ndev)) rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); if (!rxe) goto drop; if (skb_linearize(skb)) { ib_device_put(&rxe->ib_dev); goto drop; } udph = udp_hdr(skb); pkt->rxe = rxe; pkt->port_num = 1; pkt->hdr = (u8 *)(udph + 1); pkt->mask = RXE_GRH_MASK; pkt->paylen = be16_to_cpu(udph->len) - sizeof(*udph); /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; drop: kfree_skb(skb); return 0; } static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port, bool ipv6) { int err; struct socket *sock; struct udp_port_cfg udp_cfg = { }; struct udp_tunnel_sock_cfg tnl_cfg = { }; if (ipv6) { udp_cfg.family = AF_INET6; udp_cfg.ipv6_v6only = 1; } else { udp_cfg.family = AF_INET; } udp_cfg.local_udp_port = port; /* Create UDP socket */ err = udp_sock_create(net, &udp_cfg, &sock); if (err < 0) return ERR_PTR(err); tnl_cfg.encap_type = 1; tnl_cfg.encap_rcv = rxe_udp_encap_recv; /* Setup UDP tunnel */ setup_udp_tunnel_sock(net, sock, &tnl_cfg); return sock; } static void rxe_release_udp_tunnel(struct socket *sk) { if (sk) udp_tunnel_sock_release(sk); } static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port, __be16 dst_port) { struct udphdr *udph; __skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); udph = udp_hdr(skb); udph->dest = dst_port; udph->source = src_port; udph->len = htons(skb->len); udph->check = 0; } static void prepare_ipv4_hdr(struct dst_entry *dst, struct sk_buff *skb, __be32 saddr, __be32 daddr, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { struct iphdr *iph; skb_scrub_packet(skb, xnet); skb_clear_hash(skb); skb_dst_set(skb, dst_clone(dst)); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = IPVERSION; iph->ihl = sizeof(struct iphdr) >> 2; iph->tot_len = htons(skb->len); iph->frag_off = df; iph->protocol = proto; iph->tos = tos; iph->daddr = daddr; iph->saddr = saddr; iph->ttl = ttl; __ip_select_ident(dev_net(dst->dev), iph, skb_shinfo(skb)->gso_segs ?: 1); } static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, __u8 proto, __u8 prio, __u8 ttl) { struct ipv6hdr *ip6h; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst_clone(dst)); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, htonl(0)); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = proto; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); } static int prepare4(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; bool xnet = false; __be16 df = htons(IP_DF); struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr; struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { rxe_dbg_qp(qp, "Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv4_hdr(dst, skb, saddr->s_addr, daddr->s_addr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit, df, xnet); dst_release(dst); return 0; } static int prepare6(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { struct rxe_qp *qp = pkt->qp; struct dst_entry *dst; struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr; struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr; dst = rxe_find_route(skb->dev, qp, av); if (!dst) { rxe_dbg_qp(qp, "Host not reachable\n"); return -EHOSTUNREACH; } prepare_udp_hdr(skb, cpu_to_be16(qp->src_port), cpu_to_be16(ROCE_V2_UDP_DPORT)); prepare_ipv6_hdr(dst, skb, saddr, daddr, IPPROTO_UDP, av->grh.traffic_class, av->grh.hop_limit); dst_release(dst); return 0; } int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err = 0; if (skb->protocol == htons(ETH_P_IP)) err = prepare4(av, pkt, skb); else if (skb->protocol == htons(ETH_P_IPV6)) err = prepare6(av, pkt, skb); if (ether_addr_equal(skb->dev->dev_addr, av->dmac)) pkt->mask |= RXE_LOOPBACK_MASK; return err; } static void rxe_skb_tx_dtor(struct sk_buff *skb) { struct net_device *ndev = skb->dev; struct rxe_dev *rxe; unsigned int qp_index; struct rxe_qp *qp; int skb_out; rxe = rxe_get_dev_from_net(ndev); if (!rxe && is_vlan_dev(ndev)) rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev)); if (WARN_ON(!rxe)) return; qp_index = (int)(uintptr_t)skb->sk->sk_user_data; if (!qp_index) return; qp = rxe_pool_get_index(&rxe->qp_pool, qp_index); if (!qp) goto put_dev; skb_out = atomic_dec_return(&qp->skb_out); if (qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW) rxe_sched_task(&qp->send_task); rxe_put(qp); put_dev: ib_device_put(&rxe->ib_dev); sock_put(skb->sk); } static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt) { int err; struct sock *sk = pkt->qp->sk->sk; sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); else err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); return err; } /* fix up a send packet to match the packets * received from UDP before looping them back */ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt) { struct sock *sk = pkt->qp->sk->sk; memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt)); sock_hold(sk); skb->sk = sk; skb->destructor = rxe_skb_tx_dtor; atomic_inc(&pkt->qp->skb_out); if (skb->protocol == htons(ETH_P_IP)) skb_pull(skb, sizeof(struct iphdr)); else skb_pull(skb, sizeof(struct ipv6hdr)); if (WARN_ON(!ib_device_try_get(&pkt->rxe->ib_dev))) { kfree_skb(skb); return -EIO; } /* remove udp header */ skb_pull(skb, sizeof(struct udphdr)); rxe_rcv(skb); return 0; } int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct sk_buff *skb) { int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); if (pkt->mask & RXE_LOOPBACK_MASK) err = rxe_loopback(skb, pkt); else err = rxe_send(skb, pkt); if (err) { rxe_counter_inc(rxe, RXE_CNT_SEND_ERR); return err; } rxe_counter_inc(rxe, RXE_CNT_SENT_PKTS); goto done; drop: kfree_skb(skb); err = 0; done: return err; } struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av, int paylen, struct rxe_pkt_info *pkt) { unsigned int hdr_len; struct sk_buff *skb = NULL; struct net_device *ndev; const struct ib_gid_attr *attr; const int port_num = 1; attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index); if (IS_ERR(attr)) return NULL; if (av->network_type == RXE_NETWORK_TYPE_IPV4) hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct iphdr); else hdr_len = ETH_HLEN + sizeof(struct udphdr) + sizeof(struct ipv6hdr); rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(attr); if (IS_ERR(ndev)) { rcu_read_unlock(); goto out; } skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev), GFP_ATOMIC); if (unlikely(!skb)) { rcu_read_unlock(); goto out; } skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev)); /* FIXME: hold reference to this netdev until life of this skb. */ skb->dev = ndev; rcu_read_unlock(); if (av->network_type == RXE_NETWORK_TYPE_IPV4) skb->protocol = htons(ETH_P_IP); else skb->protocol = htons(ETH_P_IPV6); pkt->rxe = rxe; pkt->port_num = port_num; pkt->hdr = skb_put(skb, paylen); pkt->mask |= RXE_GRH_MASK; out: rdma_put_gid_attr(attr); return skb; } /* * this is required by rxe_cfg to match rxe devices in * /sys/class/infiniband up with their underlying ethernet devices */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { struct net_device *ndev; char *ndev_name; ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); if (!ndev) return NULL; ndev_name = ndev->name; dev_put(ndev); return ndev_name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) { int err; struct rxe_dev *rxe = NULL; rxe = ib_alloc_device(rxe_dev, ib_dev); if (!rxe) return -ENOMEM; ib_mark_name_assigned_by_user(&rxe->ib_dev); err = rxe_add(rxe, ndev->mtu, ibdev_name, ndev); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; } return 0; } static void rxe_port_event(struct rxe_dev *rxe, enum ib_event_type event) { struct ib_event ev; ev.device = &rxe->ib_dev; ev.element.port_num = 1; ev.event = event; ib_dispatch_event(&ev); } /* Caller must hold net_info_lock */ void rxe_port_up(struct rxe_dev *rxe) { rxe_port_event(rxe, IB_EVENT_PORT_ACTIVE); dev_info(&rxe->ib_dev.dev, "set active\n"); } /* Caller must hold net_info_lock */ void rxe_port_down(struct rxe_dev *rxe) { rxe_port_event(rxe, IB_EVENT_PORT_ERR); rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); dev_info(&rxe->ib_dev.dev, "set down\n"); } void rxe_set_port_state(struct rxe_dev *rxe) { struct net_device *ndev; ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); if (!ndev) return; if (ib_get_curr_port_state(ndev) == IB_PORT_ACTIVE) rxe_port_up(rxe); else rxe_port_down(rxe); dev_put(ndev); } static int rxe_notify(struct notifier_block *not_blk, unsigned long event, void *arg) { struct net_device *ndev = netdev_notifier_info_to_dev(arg); struct rxe_dev *rxe = rxe_get_dev_from_net(ndev); if (!rxe) return NOTIFY_OK; switch (event) { case NETDEV_UNREGISTER: ib_unregister_device_queued(&rxe->ib_dev); break; case NETDEV_CHANGEMTU: rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); rxe_set_mtu(rxe, ndev->mtu); break; case NETDEV_DOWN: case NETDEV_CHANGE: if (ib_get_curr_port_state(ndev) == IB_PORT_DOWN) rxe_counter_inc(rxe, RXE_CNT_LINK_DOWNED); break; case NETDEV_REBOOT: case NETDEV_GOING_DOWN: case NETDEV_CHANGEADDR: case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: default: rxe_dbg_dev(rxe, "ignoring netdev event = %ld for %s\n", event, ndev->name); break; } ib_device_put(&rxe->ib_dev); return NOTIFY_OK; } static struct notifier_block rxe_net_notifier = { .notifier_call = rxe_notify, }; static int rxe_net_ipv4_init(void) { recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false); if (IS_ERR(recv_sockets.sk4)) { recv_sockets.sk4 = NULL; pr_err("Failed to create IPv4 UDP tunnel\n"); return -1; } return 0; } static int rxe_net_ipv6_init(void) { #if IS_ENABLED(CONFIG_IPV6) recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true); if (PTR_ERR(recv_sockets.sk6) == -EAFNOSUPPORT) { recv_sockets.sk6 = NULL; pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n"); return 0; } if (IS_ERR(recv_sockets.sk6)) { recv_sockets.sk6 = NULL; pr_err("Failed to create IPv6 UDP tunnel\n"); return -1; } #endif return 0; } void rxe_net_exit(void) { rxe_release_udp_tunnel(recv_sockets.sk6); rxe_release_udp_tunnel(recv_sockets.sk4); unregister_netdevice_notifier(&rxe_net_notifier); } int rxe_net_init(void) { int err; recv_sockets.sk6 = NULL; err = rxe_net_ipv4_init(); if (err) return err; err = rxe_net_ipv6_init(); if (err) goto err_out; err = register_netdevice_notifier(&rxe_net_notifier); if (err) { pr_err("Failed to register netdev notifier\n"); goto err_out; } return 0; err_out: rxe_net_exit(); return err; } |
| 245 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sock #if !defined(_TRACE_SOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SOCK_H #include <net/sock.h> #include <net/ipv6.h> #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> #include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ EMe(AF_INET6) /* The protocol traced by inet_sock_set_state */ #define inet_protocol_names \ EM(IPPROTO_TCP) \ EM(IPPROTO_DCCP) \ EM(IPPROTO_SCTP) \ EMe(IPPROTO_MPTCP) #define tcp_state_names \ EM(TCP_ESTABLISHED) \ EM(TCP_SYN_SENT) \ EM(TCP_SYN_RECV) \ EM(TCP_FIN_WAIT1) \ EM(TCP_FIN_WAIT2) \ EM(TCP_TIME_WAIT) \ EM(TCP_CLOSE) \ EM(TCP_CLOSE_WAIT) \ EM(TCP_LAST_ACK) \ EM(TCP_LISTEN) \ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) #define skmem_kind_names \ EM(SK_MEM_SEND) \ EMe(SK_MEM_RECV) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); family_names inet_protocol_names tcp_state_names skmem_kind_names #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } #define show_family_name(val) \ __print_symbolic(val, family_names) #define show_inet_protocol_name(val) \ __print_symbolic(val, inet_protocol_names) #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) #define show_skmem_kind_names(val) \ __print_symbolic(val, skmem_kind_names) TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(int, rmem_alloc) __field(unsigned int, truesize) __field(int, sk_rcvbuf) ), TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", __entry->rmem_alloc, __entry->truesize, __entry->sk_rcvbuf) ); TRACE_EVENT(sock_exceed_buf_limit, TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) __field(int, sysctl_wmem) __field(int, wmem_alloc) __field(int, wmem_queued) __field(int, kind) ), TP_fast_assign( strscpy(__entry->name, prot->name, 32); __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, __entry->rmem_alloc, __entry->sysctl_wmem, __entry->wmem_alloc, __entry->wmem_queued, show_skmem_kind_names(__entry->kind) ) ); TRACE_EVENT(inet_sock_set_state, TP_PROTO(const struct sock *sk, const int oldstate, const int newstate), TP_ARGS(sk, oldstate, newstate), TP_STRUCT__entry( __field(const void *, skaddr) __field(int, oldstate) __field(int, newstate) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->oldstate = oldstate; __entry->newstate = newstate; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->oldstate), show_tcp_state_name(__entry->newstate)) ); TRACE_EVENT(inet_sk_error_report, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(int, error) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->error = sk->sk_err; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->error) ); TRACE_EVENT(sk_data_ready, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, family) __field(__u16, protocol) __field(unsigned long, ip) ), TP_fast_assign( __entry->skaddr = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ip = _RET_IP_; ), TP_printk("family=%u protocol=%u func=%ps", __entry->family, __entry->protocol, (void *)__entry->ip) ); /* * sock send/recv msg length */ DECLARE_EVENT_CLASS(sock_msg_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags), TP_STRUCT__entry( __field(void *, sk) __field(__u16, family) __field(__u16, protocol) __field(int, ret) __field(int, flags) ), TP_fast_assign( __entry->sk = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ret = ret; __entry->flags = flags; ), TP_printk("sk address = %p, family = %s protocol = %s, length = %d, error = %d, flags = 0x%x", __entry->sk, show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), !(__entry->flags & MSG_PEEK) ? (__entry->ret > 0 ? __entry->ret : 0) : 0, __entry->ret < 0 ? __entry->ret : 0, __entry->flags) ); DEFINE_EVENT(sock_msg_length, sock_send_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); DEFINE_EVENT(sock_msg_length, sock_recv_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 11 11 11 11 11 11 11 11 11 11 11 1 10 1 1 1 245 245 245 245 244 245 245 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 | // 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. * * Generic socket support routines. Memory allocators, socket lock/release * handler for protocols to use and generic option handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Fixes: * Alan Cox : Numerous verify_area() problems * Alan Cox : Connecting on a connecting socket * now returns an error for tcp. * Alan Cox : sock->protocol is set correctly. * and is not sometimes left as 0. * Alan Cox : connect handles icmp errors on a * connect properly. Unfortunately there * is a restart syscall nasty there. I * can't match BSD without hacking the C * library. Ideas urgently sought! * Alan Cox : Disallow bind() to addresses that are * not ours - especially broadcast ones!! * Alan Cox : Socket 1024 _IS_ ok for users. (fencepost) * Alan Cox : sock_wfree/sock_rfree don't destroy sockets, * instead they leave that for the DESTROY timer. * Alan Cox : Clean up error flag in accept * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. * Alan Cox : Added zapped flag for TCP * Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code * Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb * Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources * Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing. * Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so... * Rick Sladkey : Relaxed UDP rules for matching packets. * C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support * Pauline Middelink : identd support * Alan Cox : Fixed connect() taking signals I think. * Alan Cox : SO_LINGER supported * Alan Cox : Error reporting fixes * Anonymous : inet_create tidied up (sk->reuse setting) * Alan Cox : inet sockets don't set sk->type! * Alan Cox : Split socket option code * Alan Cox : Callbacks * Alan Cox : Nagle flag for Charles & Johannes stuff * Alex : Removed restriction on inet fioctl * Alan Cox : Splitting INET from NET core * Alan Cox : Fixed bogus SO_TYPE handling in getsockopt() * Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code * Alan Cox : Split IP from generic code * Alan Cox : New kfree_skbmem() * Alan Cox : Make SO_DEBUG superuser only. * Alan Cox : Allow anyone to clear SO_DEBUG * (compatibility fix) * Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput. * Alan Cox : Allocator for a socket is settable. * Alan Cox : SO_ERROR includes soft errors. * Alan Cox : Allow NULL arguments on some SO_ opts * Alan Cox : Generic socket allocation to make hooks * easier (suggested by Craig Metz). * Michael Pall : SO_ERROR returns positive errno again * Steve Whitehouse: Added default destructor to free * protocol private data. * Steve Whitehouse: Added various other default routines * common to several socket families. * Chris Evans : Call suser() check last on F_SETOWN * Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER. * Andi Kleen : Add sock_kmalloc()/sock_kfree_s() * Andi Kleen : Fix write_space callback * Chris Evans : Security fixes - signedness again * Arnaldo C. Melo : cleanups, use skb_queue_purge * * To Fix: */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/unaligned.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/poll.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> #include <linux/static_key.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> #include <linux/compat.h> #include <linux/mroute.h> #include <linux/mroute6.h> #include <linux/icmpv6.h> #include <linux/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> #include <net/proto_memory.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> #include <net/netprio_cgroup.h> #include <linux/sock_diag.h> #include <linux/filter.h> #include <net/sock_reuseport.h> #include <net/bpf_sk_storage.h> #include <trace/events/sock.h> #include <net/tcp.h> #include <net/busy_poll.h> #include <net/phonet/phonet.h> #include <linux/ethtool.h> #include "dev.h" static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); static void sock_def_write_space_wfree(struct sock *sk); static void sock_def_write_space(struct sock *sk); /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in the user * namespace @user_ns. */ bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap) { return file_ns_capable(sk->sk_socket->file, user_ns, cap) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(sk_ns_capable); /** * sk_capable - Socket global capability test * @sk: Socket to use a capability on or through * @cap: The global capability to use * * Test to see if the opener of the socket had when the socket was * created and the current process has the capability @cap in all user * namespaces. */ bool sk_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, &init_user_ns, cap); } EXPORT_SYMBOL(sk_capable); /** * sk_net_capable - Network namespace socket capability test * @sk: Socket to use a capability on or through * @cap: The capability to use * * Test to see if the opener of the socket had when the socket was created * and the current process has the capability @cap over the network namespace * the socket is a member of. */ bool sk_net_capable(const struct sock *sk, int cap) { return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); } EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have * one slock key per address family and separate keys for internal and * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ #define _sock_locks(x) \ x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ x "27" , x "28" , x "AF_CAN" , \ x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ x "AF_MCTP" , \ x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { _sock_locks("clock-") }; static const char *const af_family_kern_key_strings[AF_MAX+1] = { _sock_locks("k-sk_lock-") }; static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { _sock_locks("k-slock-") }; static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { _sock_locks("k-clock-") }; static const char *const af_family_rlock_key_strings[AF_MAX+1] = { _sock_locks("rlock-") }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { _sock_locks("wlock-") }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { _sock_locks("elock-") }; /* * sk_callback_lock and sk queues locking rules are per-address-family, * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; static struct lock_class_key af_rlock_keys[AF_MAX]; static struct lock_class_key af_wlock_keys[AF_MAX]; static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC * @sk: socket to set it on * * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. * It's the responsibility of the admin to adjust min_free_kbytes * to meet the requirements */ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward * progress of swapping. SOCK_MEMALLOC may be cleared while * it has rmem allocations due to the last swapfile being deactivated * but there is a risk that the socket is unusable due to exceeding * the rmem limits. Reclaim the reserves and obey rmem limits again. */ sk_mem_reclaim(sk); } EXPORT_SYMBOL_GPL(sk_clear_memalloc); int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { int ret; unsigned int noreclaim_flag; /* these should have been dropped before queueing */ BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); noreclaim_flag = memalloc_noreclaim_save(); ret = INDIRECT_CALL_INET(sk->sk_backlog_rcv, tcp_v6_do_rcv, tcp_v4_do_rcv, sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); void sk_error_report(struct sock *sk) { sk->sk_error_report(sk); switch (sk->sk_family) { case AF_INET: fallthrough; case AF_INET6: trace_inet_sk_error_report(sk); break; default: break; } } EXPORT_SYMBOL(sk_error_report); int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; tv.tv_usec = 0; } else { tv.tv_sec = timeo / HZ; tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); } if (old_timeval) { struct __kernel_old_timeval old_tv; old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; return sizeof(old_tv); } *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } EXPORT_SYMBOL(sock_get_timeout); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval) { if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) return -EINVAL; if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; tv->tv_sec = tv32.tv_sec; tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; if (optlen < sizeof(old_tv)) return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; tv->tv_sec = old_tv.tv_sec; tv->tv_usec = old_tv.tv_usec; } else { if (optlen < sizeof(*tv)) return -EINVAL; if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } return 0; } EXPORT_SYMBOL(sock_copy_user_timeval); static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); long val; if (err) return err; if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; WRITE_ONCE(*timeo_p, 0); if (warned < 10 && net_ratelimit()) { warned++; pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", __func__, current->comm, task_pid_nr(current)); } return 0; } val = MAX_SCHEDULE_TIMEOUT; if ((tv.tv_sec || tv.tv_usec) && (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))) val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); WRITE_ONCE(*timeo_p, val); return 0; } static bool sk_set_prio_allowed(const struct sock *sk, int val) { return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) || sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); } static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { case AF_UNSPEC: case AF_UNIX: return false; default: return true; } } static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; if (sock_needs_netstamp(sk) && !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= READ_ONCE(sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } skb->dev = NULL; skb_set_owner_r(skb, sk); /* we escape from rcu protected region, make sure we dont leak * a norefcounted dst */ skb_dst_force(skb); spin_lock_irqsave(&list->lock, flags); sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(__sock_queue_rcv_skb); int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { enum skb_drop_reason drop_reason; int err; err = sk_filter(sk, skb); if (err) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto out; } err = __sock_queue_rcv_skb(sk, skb); switch (err) { case -ENOMEM: drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; break; case -ENOBUFS: drop_reason = SKB_DROP_REASON_PROTO_MEM; break; default: drop_reason = SKB_NOT_DROPPED_YET; break; } out: if (reason) *reason = drop_reason; return err; } EXPORT_SYMBOL(sock_queue_rcv_skb_reason); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { int rc = NET_RX_SUCCESS; if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } if (nested) bh_lock_sock_nested(sk); else bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* * trylock + unlock semantics: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; } bh_unlock_sock(sk); out: if (refcounted) sock_put(sk); return rc; discard_and_relse: kfree_skb(skb); goto out; } EXPORT_SYMBOL(__sk_receive_skb); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *, u32)); INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(__sk_dst_check); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk_dst_get(sk); if (dst && dst->obsolete && INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_dst_reset(sk); dst_release(dst); return NULL; } return dst; } EXPORT_SYMBOL(sk_dst_check); static int sock_bindtoindex_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); /* Sorry... */ ret = -EPERM; if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; if (ifindex < 0) goto out; /* Paired with all READ_ONCE() done locklessly. */ WRITE_ONCE(sk->sk_bound_dev_if, ifindex); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); sk_dst_reset(sk); ret = 0; out: #endif return ret; } int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk) { int ret; if (lock_sk) lock_sock(sk); ret = sock_bindtoindex_locked(sk, ifindex); if (lock_sk) release_sock(sk); return ret; } EXPORT_SYMBOL(sock_bindtoindex); static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; ret = -EINVAL; if (optlen < 0) goto out; /* Bind this socket to a particular device like "eth0", * as specified in the passed interface name. If the * name is "" or the option length is zero the socket * is not bound. */ if (optlen > IFNAMSIZ - 1) optlen = IFNAMSIZ - 1; memset(devname, 0, sizeof(devname)); ret = -EFAULT; if (copy_from_sockptr(devname, optval, optlen)) goto out; index = 0; if (devname[0] != '\0') { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, devname); if (dev) index = dev->ifindex; rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; } sockopt_lock_sock(sk); ret = sock_bindtoindex_locked(sk, index); sockopt_release_sock(sk); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(const struct sock *sk) |