1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 #ifndef __NET_SCHED_CODEL_IMPL_H #define __NET_SCHED_CODEL_IMPL_H /* * Codel - The Controlled-Delay Active Queue Management algorithm * * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> * * 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, * without modification. * 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. The names of the authors may not 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. * * 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. * */ /* Controlling Queue Delay (CoDel) algorithm * ========================================= * Source : Kathleen Nichols and Van Jacobson * http://queue.acm.org/detail.cfm?id=2209336 * * Implemented on linux by Dave Taht and Eric Dumazet */ static void codel_params_init(struct codel_params *params) { params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; params->ecn = false; } static void codel_vars_init(struct codel_vars *vars) { memset(vars, 0, sizeof(*vars)); } static void codel_stats_init(struct codel_stats *stats) { stats->maxpacket = 0; } /* * http://en.wikipedia.org/wiki/Methods_of_computing_square_roots#Iterative_methods_for_reciprocal_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 */ static void codel_Newton_step(struct codel_vars *vars) { u32 invsqrt = ((u32)vars->rec_inv_sqrt) << REC_INV_SQRT_SHIFT; u32 invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; u64 val = (3LL << 32) - ((u64)vars->count * invsqrt2); val >>= 2; /* avoid overflow in following multiply */ val = (val * invsqrt) >> (32 - 2 + 1); vars->rec_inv_sqrt = val >> REC_INV_SQRT_SHIFT; } /* * CoDel control_law is t + interval/sqrt(count) * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid * both sqrt() and divide operation. */ static codel_time_t codel_control_law(codel_time_t t, codel_time_t interval, u32 rec_inv_sqrt) { return t + reciprocal_scale(interval, rec_inv_sqrt << REC_INV_SQRT_SHIFT); } static bool codel_should_drop(const struct sk_buff *skb, void *ctx, struct codel_vars *vars, struct codel_params *params, struct codel_stats *stats, codel_skb_len_t skb_len_func, codel_skb_time_t skb_time_func, u32 *backlog, codel_time_t now) { bool ok_to_drop; u32 skb_len; if (!skb) { vars->first_above_time = 0; return false; } skb_len = skb_len_func(skb); vars->ldelay = now - skb_time_func(skb); if (unlikely(skb_len > stats->maxpacket)) stats->maxpacket = skb_len; if (codel_time_before(vars->ldelay, params->target) || *backlog <= params->mtu) { /* went below - stay below for at least interval */ vars->first_above_time = 0; return false; } ok_to_drop = false; if (vars->first_above_time == 0) { /* just went above from below. If we stay above * for at least interval we'll say it's ok to drop */ vars->first_above_time = now + params->interval; } else if (codel_time_after(now, vars->first_above_time)) { ok_to_drop = true; } return ok_to_drop; } static struct sk_buff *codel_dequeue(void *ctx, u32 *backlog, struct codel_params *params, struct codel_vars *vars, struct codel_stats *stats, codel_skb_len_t skb_len_func, codel_skb_time_t skb_time_func, codel_skb_drop_t drop_func, codel_skb_dequeue_t dequeue_func) { struct sk_buff *skb = dequeue_func(vars, ctx); codel_time_t now; bool drop; if (!skb) { vars->dropping = false; return skb; } now = codel_get_time(); drop = codel_should_drop(skb, ctx, vars, params, stats, skb_len_func, skb_time_func, backlog, now); if (vars->dropping) { if (!drop) { /* sojourn time below target - leave dropping state */ vars->dropping = false; } else if (codel_time_after_eq(now, vars->drop_next)) { /* It's time for the next drop. Drop the current * packet and dequeue the next. The dequeue might * take us out of dropping state. * If not, schedule the next drop. * A large backlog might result in drop rates so high * that the next drop should happen now, * hence the while loop. */ while (vars->dropping && codel_time_after_eq(now, vars->drop_next)) { vars->count++; /* dont care of possible wrap * since there is no more divide */ codel_Newton_step(vars); if (params->ecn && INET_ECN_set_ce(skb)) { stats->ecn_mark++; vars->drop_next = codel_control_law(vars->drop_next, params->interval, vars->rec_inv_sqrt); goto end; } stats->drop_len += skb_len_func(skb); drop_func(skb, ctx); stats->drop_count++; skb = dequeue_func(vars, ctx); if (!codel_should_drop(skb, ctx, vars, params, stats, skb_len_func, skb_time_func, backlog, now)) { /* leave dropping state */ vars->dropping = false; } else { /* and schedule the next drop */ vars->drop_next = codel_control_law(vars->drop_next, params->interval, vars->rec_inv_sqrt); } } } } else if (drop) { u32 delta; if (params->ecn && INET_ECN_set_ce(skb)) { stats->ecn_mark++; } else { stats->drop_len += skb_len_func(skb); drop_func(skb, ctx); stats->drop_count++; skb = dequeue_func(vars, ctx); drop = codel_should_drop(skb, ctx, vars, params, stats, skb_len_func, skb_time_func, backlog, now); } vars->dropping = true; /* if min went above target close to when we last went below it * assume that the drop rate that controlled the queue on the * last cycle is a good starting point to control it now. */ delta = vars->count - vars->lastcount; if (delta > 1 && codel_time_before(now - vars->drop_next, 16 * params->interval)) { vars->count = delta; /* we dont care if rec_inv_sqrt approximation * is not very precise : * Next Newton steps will correct it quadratically. */ codel_Newton_step(vars); } else { vars->count = 1; vars->rec_inv_sqrt = ~0U >> REC_INV_SQRT_SHIFT; } vars->lastcount = vars->count; vars->drop_next = codel_control_law(now, params->interval, vars->rec_inv_sqrt); } end: if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && INET_ECN_set_ce(skb)) stats->ce_mark++; return skb; } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NSPROXY_H #define _LINUX_NSPROXY_H #include <linux/spinlock.h> #include <linux/sched.h> struct mnt_namespace; struct uts_namespace; struct ipc_namespace; struct pid_namespace; struct cgroup_namespace; struct fs_struct; /* * A structure to contain pointers to all per-process * namespaces - fs (mount), uts, network, sysvipc, etc. * * The pid namespace is an exception -- it's accessed using * task_active_pid_ns. The pid namespace here is the * namespace that children will use. * * 'count' is the number of tasks holding a reference. * The count for each namespace, then, will be the number * of nsproxies pointing to it, not the number of tasks. * * The nsproxy is shared by tasks which share all namespaces. * As soon as a single namespace is cloned or unshared, the * nsproxy is copied. */ struct nsproxy { atomic_t count; struct uts_namespace *uts_ns; struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns_for_children; struct net *net_ns; struct time_namespace *time_ns; struct time_namespace *time_ns_for_children; struct cgroup_namespace *cgroup_ns; }; extern struct nsproxy init_nsproxy; /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. * * If a new user namespace is requested cred will * point to a modifiable set of credentials. If a pointer * to a modifiable set is needed nsset_cred() must be * used and tested. */ struct nsset { unsigned flags; struct nsproxy *nsproxy; struct fs_struct *fs; const struct cred *cred; }; static inline struct cred *nsset_cred(struct nsset *set) { if (set->flags & CLONE_NEWUSER) return (struct cred *)set->cred; return NULL; } /* * the namespaces access rules are: * * 1. only current task is allowed to change tsk->nsproxy pointer or * any pointer on the nsproxy itself. Current must hold the task_lock * when changing tsk->nsproxy. * * 2. when accessing (i.e. reading) current task's namespaces - no * precautions should be taken - just dereference the pointers * * 3. the access to other task namespaces is performed like this * task_lock(task); * nsproxy = task->nsproxy; * if (nsproxy != NULL) { * / * * * work with the namespaces here * * e.g. get the reference on one of them * * / * } / * * * NULL task->nsproxy means that this task is * * almost dead (zombie) * * / * task_unlock(task); * */ int copy_namespaces(unsigned long flags, struct task_struct *tsk); void exit_task_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { if (atomic_dec_and_test(&ns->count)) { free_nsproxy(ns); } } static inline void get_nsproxy(struct nsproxy *ns) { atomic_inc(&ns->count); } #endif
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLY__ #include <asm/nospec-branch.h> /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __section(".cpuidle.text") /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern __always_inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : "=rm" (flags) : /* no input */ : "memory"); return flags; } extern inline void native_restore_fl(unsigned long flags); extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ :"g" (flags) :"memory", "cc"); } static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static __always_inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static inline __cpuidle void native_safe_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { mds_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } #endif #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline unsigned long arch_local_save_flags(void) { return native_save_fl(); } static __always_inline void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); } static __always_inline void arch_local_irq_enable(void) { native_irq_enable(); } /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static inline __cpuidle void halt(void) { native_halt(); } /* * For spinlocks, etc: */ static __always_inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(x) pushfq; popq %rax #endif #define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; #define USERGS_SYSRET32 \ swapgs; \ sysretl #else #define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static __always_inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } #else #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV #else #define SWAPGS swapgs #endif #endif #endif /* !__ASSEMBLY__ */ #endif
1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; unsigned int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX struct mem_cgroup_id { int id; refcount_t ref; }; /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremented by the number of pages. This counter is used * to trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_NTARGETS, }; struct memcg_vmstats_percpu { long stat[MEMCG_NR_STAT]; unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ unsigned int generation; }; struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; /* * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. */ struct memcg_shrinker_map { struct rcu_head rcu; unsigned long map[]; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; /* Legacy local VM stats */ struct lruvec_stat __percpu *lruvec_stat_local; /* Subtree VM stats (batched updates) */ struct lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; struct memcg_shrinker_map __rcu *shrinker_map; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; enum memcg_kmem_state { KMEM_NONE, KMEM_ALLOCATED, KMEM_ONLINE, }; #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define MEMCG_PADDING(name) struct memcg_padding name; #else #define MEMCG_PADDING(name) #endif /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; struct rcu_head rcu; }; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ /* Range enforcement for interrupt charges */ struct work_struct high_work; unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; int swappiness; /* OOM-Killer disable */ int oom_kill_disable; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; /* taken only while moving_account > 0 */ spinlock_t move_lock; unsigned long move_lock_flags; MEMCG_PADDING(_pad1_); atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; struct list_head objcg_list; /* list of inherited objcgs */ #endif MEMCG_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; struct task_struct *move_lock_task; /* Legacy local VM stats and events */ struct memcg_vmstats_percpu __percpu *vmstats_local; /* Subtree VM stats and events (batched updates) */ struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ #define MEMCG_CHARGE_BATCH 32U extern struct mem_cgroup *root_mem_cgroup; static __always_inline bool memcg_stat_item_in_bytes(int idx) { if (idx == MEMCG_PERCPU_B) return true; return vmstat_item_in_bytes(idx); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; if (mem_cgroup_disabled()) return; /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_protected calculation is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. */ return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg); } static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { if (!mem_cgroup_supports_protection(memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) { if (!mem_cgroup_supports_protection(memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); static struct mem_cgroup_per_node * mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) { return memcg->nodeinfo[nid]; } /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @memcg & * @node combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { percpu_ref_get(&objcg->refcnt); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { percpu_ref_put(&objcg->refcnt); } /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released: * e.g. acquire the rcu_read_lock or css_set_lock. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { return READ_ONCE(objcg->memcg); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); int mem_cgroup_scan_tasks(struct mem_cgroup *, int (*)(struct task_struct *, void *), void *); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root or the memory * controller is in legacy no-hierarchy mode. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { if (!memcg->memory.parent) return NULL; return mem_cgroup_from_counter(memcg->memory.parent, memory); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; if (!root->use_hierarchy) return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return !!(memcg->css.flags & CSS_ONLINE); } /* * For memory reclaim. */ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); unsigned long mem_cgroup_size(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { long x = atomic_long_read(&memcg->vmstats[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { long x = 0; int cpu; for_each_possible_cpu(cpu) x += per_cpu(memcg->vmstats_local->stat[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_state(memcg, idx, val); local_irq_restore(flags); } /** * mod_memcg_page_state - update page state statistics * @page: the page * @idx: page state item to account * @val: number of pages (positive or negative) * * The @page must be locked or the caller must use lock_page_memcg() * to prevent double accounting when the page is concurrently being * moved to another memcg: * * lock_page(page) or lock_page_memcg(page) * if (TestClearPageState(page)) * mod_memcg_page_state(page, state, -1); * unlock_page(page) or unlock_page_memcg(page) * * Kernel pages are an exception to this, since they'll never move. */ static inline void __mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) __mod_memcg_state(page->mem_cgroup, idx, val); } static inline void mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); x = atomic_long_read(&pn->lruvec_stat[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x = 0; int cpu; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); for_each_possible_cpu(cpu) x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); void mod_memcg_obj_state(void *p, int idx, int val); static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_slab_state(p, idx, val); local_irq_restore(flags); } static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_page_state(page, idx, val); local_irq_restore(flags); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { unsigned long flags; local_irq_save(flags); __count_memcg_events(memcg, idx, count); local_irq_restore(flags); } static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, 1); rcu_read_unlock(); } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || event == MEMCG_SWAP_FAIL; atomic_long_inc(&memcg->memory_events_local[event]); if (!swap_event) cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); if (swap_event) cgroup_file_notify(&memcg->swap_events_file); else cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *head, unsigned int nr); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 struct mem_cgroup; static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) { return false; } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; } static inline void mem_cgroup_uncharge(struct page *page) { } static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) { return NULL; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { return 0; } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline struct mem_cgroup *lock_page_memcg(struct page *page) { return NULL; } static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } static inline void unlock_page_memcg(struct page *page) { } static inline void mem_cgroup_handle_over_high(void) { } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { return 0; } static inline void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void __mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { } static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_memcg_obj_state(void *p, int idx, int val) { } static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline void split_page_memcg(struct page *head, unsigned int nr) { } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_page_event(struct page *page, int idx) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG */ /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, -1); } static inline void __inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, 1); } static inline void __dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, -1); } static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, 1); } static inline void __dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, -1); } static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, 1); } static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, -1); } static inline void inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, 1); } static inline void dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, -1); } static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, 1); } static inline void dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, -1); } static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { if (mem_cgroup_disabled()) return; if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { if (time_before(jiffies, memcg->socket_pressure)) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; } extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; } static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } #endif #ifdef CONFIG_MEMCG_KMEM int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages); void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still * check if the cache is valid (it is either valid or NULL). * the slab_mutex must be held when looping through those caches */ #define for_each_memcg_cache_index(_idx) \ for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_enabled()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge_page(page, order); } static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages) { if (memcg_kmem_enabled()) return __memcg_kmem_charge(memcg, gfp, nr_pages); return 0; } static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge(memcg, nr_pages); } /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function * will return -1 when this is not a kmem-limited memcg. */ static inline int memcg_cache_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_obj(void *p); #else static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) static inline bool memcg_kmem_enabled(void) { return false; } static inline int memcg_cache_id(struct mem_cgroup *memcg) { return -1; } static inline void memcg_get_cache_ids(void) { } static inline void memcg_put_cache_ids(void) { } static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; } #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_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 #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tcp #if !defined(_TRACE_TCP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TCP_H #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/tracepoint.h> #include <net/ipv6.h> #include <net/tcp.h> #include <linux/sock_diag.h> #define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ do { \ struct in6_addr *pin6; \ \ pin6 = (struct in6_addr *)__entry->saddr_v6; \ ipv6_addr_set_v4mapped(saddr, pin6); \ pin6 = (struct in6_addr *)__entry->daddr_v6; \ ipv6_addr_set_v4mapped(daddr, pin6); \ } while (0) #if IS_ENABLED(CONFIG_IPV6) #define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ do { \ if (sk->sk_family == AF_INET6) { \ struct in6_addr *pin6; \ \ pin6 = (struct in6_addr *)__entry->saddr_v6; \ *pin6 = saddr6; \ pin6 = (struct in6_addr *)__entry->daddr_v6; \ *pin6 = daddr6; \ } else { \ TP_STORE_V4MAPPED(__entry, saddr, daddr); \ } \ } while (0) #else #define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ TP_STORE_V4MAPPED(__entry, saddr, daddr) #endif /* * tcp event with arguments sk and skb * * Note: this class requires a valid sk pointer; while skb pointer could * be NULL. */ DECLARE_EVENT_CLASS(tcp_event_sk_skb, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(const void *, skbaddr) __field(const void *, skaddr) __field(int, state) __field(__u16, sport) __field(__u16, dport) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skbaddr = skb; __entry->skaddr = sk; __entry->state = sk->sk_state; __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("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->state)) ); DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); /* * skb of trace_tcp_send_reset is the skb that caused RST. In case of * active reset, skb should be NULL */ DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset, TP_PROTO(const struct sock *sk, const struct sk_buff *skb), TP_ARGS(sk, skb) ); /* * tcp event with arguments sk * * Note: this class requires a valid sk pointer. */ DECLARE_EVENT_CLASS(tcp_event_sk, TP_PROTO(struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) __field(__u64, sock_cookie) ), TP_fast_assign( struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __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); __entry->sock_cookie = sock_gen_cookie(sk); ), TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c sock_cookie=%llx", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->sock_cookie) ); DEFINE_EVENT(tcp_event_sk, tcp_receive_reset, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_rcv_space_adjust, TP_PROTO(struct sock *sk), TP_ARGS(sk) ); TRACE_EVENT(tcp_retransmit_synack, TP_PROTO(const struct sock *sk, const struct request_sock *req), TP_ARGS(sk, req), TP_STRUCT__entry( __field(const void *, skaddr) __field(const void *, req) __field(__u16, sport) __field(__u16, dport) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( struct inet_request_sock *ireq = inet_rsk(req); __be32 *p32; __entry->skaddr = sk; __entry->req = req; __entry->sport = ireq->ir_num; __entry->dport = ntohs(ireq->ir_rmt_port); p32 = (__be32 *) __entry->saddr; *p32 = ireq->ir_loc_addr; p32 = (__be32 *) __entry->daddr; *p32 = ireq->ir_rmt_addr; TP_STORE_ADDRS(__entry, ireq->ir_loc_addr, ireq->ir_rmt_addr, ireq->ir_v6_loc_addr, ireq->ir_v6_rmt_addr); ), TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6) ); #include <trace/events/net_probe_common.h> TRACE_EVENT(tcp_probe, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u32, mark) __field(__u16, data_len) __field(__u32, snd_nxt) __field(__u32, snd_una) __field(__u32, snd_cwnd) __field(__u32, ssthresh) __field(__u32, snd_wnd) __field(__u32, srtt) __field(__u32, rcv_wnd) __field(__u64, sock_cookie) ), TP_fast_assign( const struct tcphdr *th = (const struct tcphdr *)skb->data; const struct inet_sock *inet = inet_sk(sk); const struct tcp_sock *tp = tcp_sk(sk); memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->mark = skb->mark; __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; __entry->snd_una = tp->snd_una; __entry->snd_cwnd = tp->snd_cwnd; __entry->snd_wnd = tp->snd_wnd; __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); __entry->srtt = tp->srtt_us >> 3; __entry->sock_cookie = sock_gen_cookie(sk); ), TP_printk("src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx", __entry->saddr, __entry->daddr, __entry->mark, __entry->data_len, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie) ); #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SWAB_H #define _UAPI_LINUX_SWAB_H #include <linux/types.h> #include <linux/compiler.h> #include <asm/bitsperlong.h> #include <asm/swab.h> /* * casts are necessary for constants, because we never know how for sure * how U/UL/ULL map to __u16, __u32, __u64. At least not in a portable way. */ #define ___constant_swab16(x) ((__u16)( \ (((__u16)(x) & (__u16)0x00ffU) << 8) | \ (((__u16)(x) & (__u16)0xff00U) >> 8))) #define ___constant_swab32(x) ((__u32)( \ (((__u32)(x) & (__u32)0x000000ffUL) << 24) | \ (((__u32)(x) & (__u32)0x0000ff00UL) << 8) | \ (((__u32)(x) & (__u32)0x00ff0000UL) >> 8) | \ (((__u32)(x) & (__u32)0xff000000UL) >> 24))) #define ___constant_swab64(x) ((__u64)( \ (((__u64)(x) & (__u64)0x00000000000000ffULL) << 56) | \ (((__u64)(x) & (__u64)0x000000000000ff00ULL) << 40) | \ (((__u64)(x) & (__u64)0x0000000000ff0000ULL) << 24) | \ (((__u64)(x) & (__u64)0x00000000ff000000ULL) << 8) | \ (((__u64)(x) & (__u64)0x000000ff00000000ULL) >> 8) | \ (((__u64)(x) & (__u64)0x0000ff0000000000ULL) >> 24) | \ (((__u64)(x) & (__u64)0x00ff000000000000ULL) >> 40) | \ (((__u64)(x) & (__u64)0xff00000000000000ULL) >> 56))) #define ___constant_swahw32(x) ((__u32)( \ (((__u32)(x) & (__u32)0x0000ffffUL) << 16) | \ (((__u32)(x) & (__u32)0xffff0000UL) >> 16))) #define ___constant_swahb32(x) ((__u32)( \ (((__u32)(x) & (__u32)0x00ff00ffUL) << 8) | \ (((__u32)(x) & (__u32)0xff00ff00UL) >> 8))) /* * Implement the following as inlines, but define the interface using * macros to allow constant folding when possible: * ___swab16, ___swab32, ___swab64, ___swahw32, ___swahb32 */ static inline __attribute_const__ __u16 __fswab16(__u16 val) { #if defined (__arch_swab16) return __arch_swab16(val); #else return ___constant_swab16(val); #endif } static inline __attribute_const__ __u32 __fswab32(__u32 val) { #if defined(__arch_swab32) return __arch_swab32(val); #else return ___constant_swab32(val); #endif } static inline __attribute_const__ __u64 __fswab64(__u64 val) { #if defined (__arch_swab64) return __arch_swab64(val); #elif defined(__SWAB_64_THRU_32__) __u32 h = val >> 32; __u32 l = val & ((1ULL << 32) - 1); return (((__u64)__fswab32(l)) << 32) | ((__u64)(__fswab32(h))); #else return ___constant_swab64(val); #endif } static inline __attribute_const__ __u32 __fswahw32(__u32 val) { #ifdef __arch_swahw32 return __arch_swahw32(val); #else return ___constant_swahw32(val); #endif } static inline __attribute_const__ __u32 __fswahb32(__u32 val) { #ifdef __arch_swahb32 return __arch_swahb32(val); #else return ___constant_swahb32(val); #endif } /** * __swab16 - return a byteswapped 16-bit value * @x: value to byteswap */ #ifdef __HAVE_BUILTIN_BSWAP16__ #define __swab16(x) (__u16)__builtin_bswap16((__u16)(x)) #else #define __swab16(x) \ (__builtin_constant_p((__u16)(x)) ? \ ___constant_swab16(x) : \ __fswab16(x)) #endif /** * __swab32 - return a byteswapped 32-bit value * @x: value to byteswap */ #ifdef __HAVE_BUILTIN_BSWAP32__ #define __swab32(x) (__u32)__builtin_bswap32((__u32)(x)) #else #define __swab32(x) \ (__builtin_constant_p((__u32)(x)) ? \ ___constant_swab32(x) : \ __fswab32(x)) #endif /** * __swab64 - return a byteswapped 64-bit value * @x: value to byteswap */ #ifdef __HAVE_BUILTIN_BSWAP64__ #define __swab64(x) (__u64)__builtin_bswap64((__u64)(x)) #else #define __swab64(x) \ (__builtin_constant_p((__u64)(x)) ? \ ___constant_swab64(x) : \ __fswab64(x)) #endif static __always_inline unsigned long __swab(const unsigned long y) { #if __BITS_PER_LONG == 64 return __swab64(y); #else /* __BITS_PER_LONG == 32 */ return __swab32(y); #endif } /** * __swahw32 - return a word-swapped 32-bit value * @x: value to wordswap * * __swahw32(0x12340000) is 0x00001234 */ #define __swahw32(x) \ (__builtin_constant_p((__u32)(x)) ? \ ___constant_swahw32(x) : \ __fswahw32(x)) /** * __swahb32 - return a high and low byte-swapped 32-bit value * @x: value to byteswap * * __swahb32(0x12345678) is 0x34127856 */ #define __swahb32(x) \ (__builtin_constant_p((__u32)(x)) ? \ ___constant_swahb32(x) : \ __fswahb32(x)) /** * __swab16p - return a byteswapped 16-bit value from a pointer * @p: pointer to a naturally-aligned 16-bit value */ static __always_inline __u16 __swab16p(const __u16 *p) { #ifdef __arch_swab16p return __arch_swab16p(p); #else return __swab16(*p); #endif } /** * __swab32p - return a byteswapped 32-bit value from a pointer * @p: pointer to a naturally-aligned 32-bit value */ static __always_inline __u32 __swab32p(const __u32 *p) { #ifdef __arch_swab32p return __arch_swab32p(p); #else return __swab32(*p); #endif } /** * __swab64p - return a byteswapped 64-bit value from a pointer * @p: pointer to a naturally-aligned 64-bit value */ static __always_inline __u64 __swab64p(const __u64 *p) { #ifdef __arch_swab64p return __arch_swab64p(p); #else return __swab64(*p); #endif } /** * __swahw32p - return a wordswapped 32-bit value from a pointer * @p: pointer to a naturally-aligned 32-bit value * * See __swahw32() for details of wordswapping. */ static inline __u32 __swahw32p(const __u32 *p) { #ifdef __arch_swahw32p return __arch_swahw32p(p); #else return __swahw32(*p); #endif } /** * __swahb32p - return a high and low byteswapped 32-bit value from a pointer * @p: pointer to a naturally-aligned 32-bit value * * See __swahb32() for details of high/low byteswapping. */ static inline __u32 __swahb32p(const __u32 *p) { #ifdef __arch_swahb32p return __arch_swahb32p(p); #else return __swahb32(*p); #endif } /** * __swab16s - byteswap a 16-bit value in-place * @p: pointer to a naturally-aligned 16-bit value */ static inline void __swab16s(__u16 *p) { #ifdef __arch_swab16s __arch_swab16s(p); #else *p = __swab16p(p); #endif } /** * __swab32s - byteswap a 32-bit value in-place * @p: pointer to a naturally-aligned 32-bit value */ static __always_inline void __swab32s(__u32 *p) { #ifdef __arch_swab32s __arch_swab32s(p); #else *p = __swab32p(p); #endif } /** * __swab64s - byteswap a 64-bit value in-place * @p: pointer to a naturally-aligned 64-bit value */ static __always_inline void __swab64s(__u64 *p) { #ifdef __arch_swab64s __arch_swab64s(p); #else *p = __swab64p(p); #endif } /** * __swahw32s - wordswap a 32-bit value in-place * @p: pointer to a naturally-aligned 32-bit value * * See __swahw32() for details of wordswapping */ static inline void __swahw32s(__u32 *p) { #ifdef __arch_swahw32s __arch_swahw32s(p); #else *p = __swahw32p(p); #endif } /** * __swahb32s - high and low byteswap a 32-bit value in-place * @p: pointer to a naturally-aligned 32-bit value * * See __swahb32() for details of high and low byte swapping */ static inline void __swahb32s(__u32 *p) { #ifdef __arch_swahb32s __arch_swahb32s(p); #else *p = __swahb32p(p); #endif } #endif /* _UAPI_LINUX_SWAB_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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mmap #if !defined(_TRACE_MMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_H #include <linux/tracepoint.h> TRACE_EVENT(vm_unmapped_area, TP_PROTO(unsigned long addr, struct vm_unmapped_area_info *info), TP_ARGS(addr, info), TP_STRUCT__entry( __field(unsigned long, addr) __field(unsigned long, total_vm) __field(unsigned long, flags) __field(unsigned long, length) __field(unsigned long, low_limit) __field(unsigned long, high_limit) __field(unsigned long, align_mask) __field(unsigned long, align_offset) ), TP_fast_assign( __entry->addr = addr; __entry->total_vm = current->mm->total_vm; __entry->flags = info->flags; __entry->length = info->length; __entry->low_limit = info->low_limit; __entry->high_limit = info->high_limit; __entry->align_mask = info->align_mask; __entry->align_offset = info->align_offset; ), TP_printk("addr=0x%lx err=%ld total_vm=0x%lx flags=0x%lx len=0x%lx lo=0x%lx hi=0x%lx mask=0x%lx ofs=0x%lx\n", IS_ERR_VALUE(__entry->addr) ? 0 : __entry->addr, IS_ERR_VALUE(__entry->addr) ? __entry->addr : 0, __entry->total_vm, __entry->flags, __entry->length, __entry->low_limit, __entry->high_limit, __entry->align_mask, __entry->align_offset) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SCSI_SCSI_REQUEST_H #define _SCSI_SCSI_REQUEST_H #include <linux/blk-mq.h> #define BLK_MAX_CDB 16 struct scsi_request { unsigned char __cmd[BLK_MAX_CDB]; unsigned char *cmd; unsigned short cmd_len; int result; unsigned int sense_len; unsigned int resid_len; /* residual count */ int retries; void *sense; }; static inline struct scsi_request *scsi_req(struct request *rq) { return blk_mq_rq_to_pdu(rq); } static inline void scsi_req_free_cmd(struct scsi_request *req) { if (req->cmd != req->__cmd) kfree(req->cmd); } void scsi_req_init(struct scsi_request *req); #endif /* _SCSI_SCSI_REQUEST_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file * Copyright (C) 2018 Intel Corporation */ #ifndef __NET_WIRELESS_NL80211_H #define __NET_WIRELESS_NL80211_H #include "core.h" int nl80211_init(void); void nl80211_exit(void); void *nl80211hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd); bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr); static inline u64 wdev_id(struct wireless_dev *wdev) { return (u64)wdev->identifier | ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32); } int nl80211_prepare_wdev_dump(struct netlink_callback *cb, struct cfg80211_registered_device **rdev, struct wireless_dev **wdev); int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct genl_info *info, struct cfg80211_chan_def *chandef); int nl80211_parse_random_mac(struct nlattr **attrs, u8 *mac_addr, u8 *mac_addr_mask); void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev, enum nl80211_commands cmd); void nl80211_notify_iface(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, enum nl80211_commands cmd); void nl80211_send_scan_start(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, bool aborted); void nl80211_send_scan_msg(struct cfg80211_registered_device *rdev, struct sk_buff *msg); void nl80211_send_sched_scan(struct cfg80211_sched_scan_request *req, u32 cmd); void nl80211_common_reg_change_event(enum nl80211_commands cmd_id, struct regulatory_request *request); static inline void nl80211_send_reg_change_event(struct regulatory_request *request) { nl80211_common_reg_change_event(NL80211_CMD_REG_CHANGE, request); } static inline void nl80211_send_wiphy_reg_change_event(struct regulatory_request *request) { nl80211_common_reg_change_event(NL80211_CMD_WIPHY_REG_CHANGE, request); } void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp); void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp, int uapsd_queues, const u8 *req_ies, size_t req_ies_len); void nl80211_send_deauth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp); void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp); void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, gfp_t gfp); void nl80211_send_assoc_timeout(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, gfp_t gfp); void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_connect_resp_params *params, gfp_t gfp); void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *addr, enum nl80211_key_type key_type, int key_id, const u8 *tsc, gfp_t gfp); void nl80211_send_beacon_hint_event(struct wiphy *wiphy, struct ieee80211_channel *channel_before, struct ieee80211_channel *channel_after); void nl80211_send_ibss_bssid(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *bssid, gfp_t gfp); int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, u32 nlpid, int freq, int sig_dbm, const u8 *buf, size_t len, u32 flags, gfp_t gfp); void nl80211_radar_notify(struct cfg80211_registered_device *rdev, const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, struct net_device *netdev, gfp_t gfp); void nl80211_send_ap_stopped(struct wireless_dev *wdev); void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev); /* peer measurement */ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info); int nl80211_pmsr_dump_results(struct sk_buff *skb, struct netlink_callback *cb); #endif /* __NET_WIRELESS_NL80211_H */
1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 /* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of the Linux kernel. * * Copyright (c) 2011-2014, Intel Corporation * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ #ifndef ASM_X86_ARCHRANDOM_H #define ASM_X86_ARCHRANDOM_H #include <asm/processor.h> #include <asm/cpufeature.h> #define RDRAND_RETRY_LOOPS 10 /* Unconditional execution of RDRAND and RDSEED */ static inline bool __must_check rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdrand_int(unsigned int *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } static inline bool __must_check rdseed_int(unsigned int *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked, * i.e. CONFIG_ARCH_RANDOM is not defined. */ #ifdef CONFIG_ARCH_RANDOM static inline bool __must_check arch_get_random_long(unsigned long *v) { return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_long(v) : false; } static inline bool __must_check arch_get_random_int(unsigned int *v) { return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_int(v) : false; } static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_long(v) : false; } static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_int(v) : false; } extern void x86_init_rdrand(struct cpuinfo_x86 *c); #else /* !CONFIG_ARCH_RANDOM */ static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { } #endif /* !CONFIG_ARCH_RANDOM */ #endif /* ASM_X86_ARCHRANDOM_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_LOCAL_H #define _ASM_X86_LOCAL_H #include <linux/percpu.h> #include <linux/atomic.h> #include <asm/asm.h> typedef struct { atomic_long_t a; } local_t; #define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } #define local_read(l) atomic_long_read(&(l)->a) #define local_set(l, i) atomic_long_set(&(l)->a, (i)) static inline void local_inc(local_t *l) { asm volatile(_ASM_INC "%0" : "+m" (l->a.counter)); } static inline void local_dec(local_t *l) { asm volatile(_ASM_DEC "%0" : "+m" (l->a.counter)); } static inline void local_add(long i, local_t *l) { asm volatile(_ASM_ADD "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } static inline void local_sub(long i, local_t *l) { asm volatile(_ASM_SUB "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } /** * local_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @l: pointer to type local_t * * Atomically subtracts @i from @l and returns * true if the result is zero, or false for all * other cases. */ static inline bool local_sub_and_test(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i); } /** * local_dec_and_test - decrement and test * @l: pointer to type local_t * * Atomically decrements @l by 1 and * returns true if the result is 0, or false for all other * cases. */ static inline bool local_dec_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e); } /** * local_inc_and_test - increment and test * @l: pointer to type local_t * * Atomically increments @l by 1 * and returns true if the result is zero, or false for all * other cases. */ static inline bool local_inc_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e); } /** * local_add_negative - add and test if negative * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static inline bool local_add_negative(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i); } /** * local_add_return - add and return * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns @i + @l */ static inline long local_add_return(long i, local_t *l) { long __i = i; asm volatile(_ASM_XADD "%0, %1;" : "+r" (i), "+m" (l->a.counter) : : "memory"); return i + __i; } static inline long local_sub_return(long i, local_t *l) { return local_add_return(-i, l); } #define local_inc_return(l) (local_add_return(1, l)) #define local_dec_return(l) (local_sub_return(1, l)) #define local_cmpxchg(l, o, n) \ (cmpxchg_local(&((l)->a.counter), (o), (n))) /* Always has a lock prefix */ #define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) /** * local_add_unless - add unless the number is a given value * @l: pointer of type local_t * @a: the amount to add to l... * @u: ...unless l is equal to u. * * Atomically adds @a to @l, so long as it was not @u. * Returns non-zero if @l was not @u, and zero otherwise. */ #define local_add_unless(l, a, u) \ ({ \ long c, old; \ c = local_read((l)); \ for (;;) { \ if (unlikely(c == (u))) \ break; \ old = local_cmpxchg((l), c, c + (a)); \ if (likely(old == c)) \ break; \ c = old; \ } \ c != (u); \ }) #define local_inc_not_zero(l) local_add_unless((l), 1, 0) /* On x86_32, these are no better than the atomic variants. * On x86-64 these are better than the atomic variants on SMP kernels * because they dont use a lock prefix. */ #define __local_inc(l) local_inc(l) #define __local_dec(l) local_dec(l) #define __local_add(i, l) local_add((i), (l)) #define __local_sub(i, l) local_sub((i), (l)) #endif /* _ASM_X86_LOCAL_H */
1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/thread_info.h> DECLARE_PER_CPU(int, __preempt_count); /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) /* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ static __always_inline int preempt_count(void) { return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { int old, new; do { old = raw_cpu_read_4(__preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old); } /* * must be macros to avoid header recursion hell */ #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* * We fold the NEED_RESCHED bit into the preempt count such that * preempt_enable() can decrement and test for needing to reschedule with a * single instruction. * * We invert the actual bit, so that when the decrement hits 0 we know we both * need to resched (the bit is cleared) and can resched (no preempt count). */ static __always_inline void set_preempt_need_resched(void) { raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* * The various preempt_count add/sub methods */ static __always_inline void __preempt_count_add(int val) { raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { raw_cpu_add_4(__preempt_count, -val); } /* * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule * a decrement which hits zero means we have no preempt_count and should * reschedule. */ static __always_inline bool __preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule_thunk(void); # define __preempt_schedule() \ asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); # define __preempt_schedule_notrace() \ asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_CLOCK_H #define _LINUX_SCHED_CLOCK_H #include <linux/smp.h> /* * Do not use outside of architecture code which knows its limitations. * * sched_clock() has no promise of monotonicity or bounded drift between * CPUs, use (which you should not) requires disabling IRQs. * * Please use one of the three interfaces below. */ extern unsigned long long notrace sched_clock(void); /* * See the comment in kernel/sched/clock.c */ extern u64 running_clock(void); extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) { } static inline void clear_sched_clock_stable(void) { } static inline void sched_clock_idle_sleep_event(void) { } static inline void sched_clock_idle_wakeup_event(void) { } static inline u64 cpu_clock(int cpu) { return sched_clock(); } static inline u64 local_clock(void) { return sched_clock(); } #else extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); /* * When sched_clock_stable(), __sched_clock_offset provides the offset * between local_clock() and sched_clock(). */ extern u64 __sched_clock_offset; extern void sched_clock_tick(void); extern void sched_clock_tick_stable(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(void); /* * As outlined in clock.c, provides a fast, high resolution, nanosecond * time source that is monotonic per cpu argument and has bounded drift * between cpus. * * ######################### BIG FAT WARNING ########################## * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # * # go backwards !! # * #################################################################### */ static inline u64 cpu_clock(int cpu) { return sched_clock_cpu(cpu); } static inline u64 local_clock(void) { return sched_clock_cpu(raw_smp_processor_id()); } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* * An i/f to runtime opt-in for irq time accounting based off of sched_clock. * The reason for this explicit opt-in is not to have perf penalty with * slow sched_clocks. */ extern void enable_sched_clock_irqtime(void); extern void disable_sched_clock_irqtime(void); #else static inline void enable_sched_clock_irqtime(void) {} static inline void disable_sched_clock_irqtime(void) {} #endif #endif /* _LINUX_SCHED_CLOCK_H */
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 // SPDX-License-Identifier: GPL-2.0 /* * Functions related to io context handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/sched/task.h> #include "blk.h" /* * For io context allocations */ static struct kmem_cache *iocontext_cachep; /** * get_io_context - increment reference count to io_context * @ioc: io_context to get * * Increment reference count to @ioc. */ void get_io_context(struct io_context *ioc) { BUG_ON(atomic_long_read(&ioc->refcount) <= 0); atomic_long_inc(&ioc->refcount); } static void icq_free_icq_rcu(struct rcu_head *head) { struct io_cq *icq = container_of(head, struct io_cq, __rcu_head); kmem_cache_free(icq->__rcu_icq_cache, icq); } /* * Exit an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_exit_icq(struct io_cq *icq) { struct elevator_type *et = icq->q->elevator->type; if (icq->flags & ICQ_EXITED) return; if (et->ops.exit_icq) et->ops.exit_icq(icq); icq->flags |= ICQ_EXITED; } /* * Release an icq. Called with ioc locked for blk-mq, and with both ioc * and queue locked for legacy. */ static void ioc_destroy_icq(struct io_cq *icq) { struct io_context *ioc = icq->ioc; struct request_queue *q = icq->q; struct elevator_type *et = q->elevator->type; lockdep_assert_held(&ioc->lock); radix_tree_delete(&ioc->icq_tree, icq->q->id); hlist_del_init(&icq->ioc_node); list_del_init(&icq->q_node); /* * Both setting lookup hint to and clearing it from @icq are done * under queue_lock. If it's not pointing to @icq now, it never * will. Hint assignment itself can race safely. */ if (rcu_access_pointer(ioc->icq_hint) == icq) rcu_assign_pointer(ioc->icq_hint, NULL); ioc_exit_icq(icq); /* * @icq->q might have gone away by the time RCU callback runs * making it impossible to determine icq_cache. Record it in @icq. */ icq->__rcu_icq_cache = et->icq_cache; icq->flags |= ICQ_DESTROYED; call_rcu(&icq->__rcu_head, icq_free_icq_rcu); } /* * Slow path for ioc release in put_io_context(). Performs double-lock * dancing to unlink all icq's and then frees ioc. */ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); spin_lock_irq(&ioc->lock); while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, struct io_cq, ioc_node); struct request_queue *q = icq->q; if (spin_trylock(&q->queue_lock)) { ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); } else { /* Make sure q and icq cannot be freed. */ rcu_read_lock(); /* Re-acquire the locks in the correct order. */ spin_unlock(&ioc->lock); spin_lock(&q->queue_lock); spin_lock(&ioc->lock); /* * The icq may have been destroyed when the ioc lock * was released. */ if (!(icq->flags & ICQ_DESTROYED)) ioc_destroy_icq(icq); spin_unlock(&q->queue_lock); rcu_read_unlock(); } } spin_unlock_irq(&ioc->lock); kmem_cache_free(iocontext_cachep, ioc); } /** * put_io_context - put a reference of io_context * @ioc: io_context to put * * Decrement reference count of @ioc and release it if the count reaches * zero. */ void put_io_context(struct io_context *ioc) { unsigned long flags; bool free_ioc = false; if (ioc == NULL) return; BUG_ON(atomic_long_read(&ioc->refcount) <= 0); /* * Releasing ioc requires reverse order double locking and we may * already be holding a queue_lock. Do it asynchronously from wq. */ if (atomic_long_dec_and_test(&ioc->refcount)) { spin_lock_irqsave(&ioc->lock, flags); if (!hlist_empty(&ioc->icq_list)) queue_work(system_power_efficient_wq, &ioc->release_work); else free_ioc = true; spin_unlock_irqrestore(&ioc->lock, flags); } if (free_ioc) kmem_cache_free(iocontext_cachep, ioc); } /** * put_io_context_active - put active reference on ioc * @ioc: ioc of interest * * Undo get_io_context_active(). If active reference reaches zero after * put, @ioc can never issue further IOs and ioscheds are notified. */ void put_io_context_active(struct io_context *ioc) { struct io_cq *icq; if (!atomic_dec_and_test(&ioc->active_ref)) { put_io_context(ioc); return; } spin_lock_irq(&ioc->lock); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; ioc_exit_icq(icq); } spin_unlock_irq(&ioc->lock); put_io_context(ioc); } /* Called by the exiting task */ void exit_io_context(struct task_struct *task) { struct io_context *ioc; task_lock(task); ioc = task->io_context; task->io_context = NULL; task_unlock(task); atomic_dec(&ioc->nr_tasks); put_io_context_active(ioc); } static void __ioc_clear_queue(struct list_head *icq_list) { unsigned long flags; rcu_read_lock(); while (!list_empty(icq_list)) { struct io_cq *icq = list_entry(icq_list->next, struct io_cq, q_node); struct io_context *ioc = icq->ioc; spin_lock_irqsave(&ioc->lock, flags); if (icq->flags & ICQ_DESTROYED) { spin_unlock_irqrestore(&ioc->lock, flags); continue; } ioc_destroy_icq(icq); spin_unlock_irqrestore(&ioc->lock, flags); } rcu_read_unlock(); } /** * ioc_clear_queue - break any ioc association with the specified queue * @q: request_queue being cleared * * Walk @q->icq_list and exit all io_cq's. */ void ioc_clear_queue(struct request_queue *q) { LIST_HEAD(icq_list); spin_lock_irq(&q->queue_lock); list_splice_init(&q->icq_list, &icq_list); spin_unlock_irq(&q->queue_lock); __ioc_clear_queue(&icq_list); } int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) { struct io_context *ioc; int ret; ioc = kmem_cache_alloc_node(iocontext_cachep, gfp_flags | __GFP_ZERO, node); if (unlikely(!ioc)) return -ENOMEM; /* initialize */ atomic_long_set(&ioc->refcount, 1); atomic_set(&ioc->nr_tasks, 1); atomic_set(&ioc->active_ref, 1); spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); /* * Try to install. ioc shouldn't be installed if someone else * already did or @task, which isn't %current, is exiting. Note * that we need to allow ioc creation on exiting %current as exit * path may issue IOs from e.g. exit_files(). The exit path is * responsible for not issuing IO after exit_io_context(). */ task_lock(task); if (!task->io_context && (task == current || !(task->flags & PF_EXITING))) task->io_context = ioc; else kmem_cache_free(iocontext_cachep, ioc); ret = task->io_context ? 0 : -EBUSY; task_unlock(task); return ret; } /** * get_task_io_context - get io_context of a task * @task: task of interest * @gfp_flags: allocation flags, used if allocation is necessary * @node: allocation node, used if allocation is necessary * * Return io_context of @task. If it doesn't exist, it is created with * @gfp_flags and @node. The returned io_context has its reference count * incremented. * * This function always goes through task_lock() and it's better to use * %current->io_context + get_io_context() for %current. */ struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) { struct io_context *ioc; might_sleep_if(gfpflags_allow_blocking(gfp_flags)); do { task_lock(task); ioc = task->io_context; if (likely(ioc)) { get_io_context(ioc); task_unlock(task); return ioc; } task_unlock(task); } while (!create_task_io_context(task, gfp_flags, node)); return NULL; } /** * ioc_lookup_icq - lookup io_cq from ioc * @ioc: the associated io_context * @q: the associated request_queue * * Look up io_cq associated with @ioc - @q pair from @ioc. Must be called * with @q->queue_lock held. */ struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q) { struct io_cq *icq; lockdep_assert_held(&q->queue_lock); /* * icq's are indexed from @ioc using radix tree and hint pointer, * both of which are protected with RCU. All removals are done * holding both q and ioc locks, and we're holding q lock - if we * find a icq which points to us, it's guaranteed to be valid. */ rcu_read_lock(); icq = rcu_dereference(ioc->icq_hint); if (icq && icq->q == q) goto out; icq = radix_tree_lookup(&ioc->icq_tree, q->id); if (icq && icq->q == q) rcu_assign_pointer(ioc->icq_hint, icq); /* allowed to race */ else icq = NULL; out: rcu_read_unlock(); return icq; } EXPORT_SYMBOL(ioc_lookup_icq); /** * ioc_create_icq - create and link io_cq * @ioc: io_context of interest * @q: request_queue of interest * @gfp_mask: allocation mask * * Make sure io_cq linking @ioc and @q exists. If icq doesn't exist, they * will be created using @gfp_mask. * * The caller is responsible for ensuring @ioc won't go away and @q is * alive and will stay alive until this function returns. */ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, gfp_t gfp_mask) { struct elevator_type *et = q->elevator->type; struct io_cq *icq; /* allocate stuff */ icq = kmem_cache_alloc_node(et->icq_cache, gfp_mask | __GFP_ZERO, q->node); if (!icq) return NULL; if (radix_tree_maybe_preload(gfp_mask) < 0) { kmem_cache_free(et->icq_cache, icq); return NULL; } icq->ioc = ioc; icq->q = q; INIT_LIST_HEAD(&icq->q_node); INIT_HLIST_NODE(&icq->ioc_node); /* lock both q and ioc and try to link @icq */ spin_lock_irq(&q->queue_lock); spin_lock(&ioc->lock); if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { hlist_add_head(&icq->ioc_node, &ioc->icq_list); list_add(&icq->q_node, &q->icq_list); if (et->ops.init_icq) et->ops.init_icq(icq); } else { kmem_cache_free(et->icq_cache, icq); icq = ioc_lookup_icq(ioc, q); if (!icq) printk(KERN_ERR "cfq: icq link failed!\n"); } spin_unlock(&ioc->lock); spin_unlock_irq(&q->queue_lock); radix_tree_preload_end(); return icq; } static int __init blk_ioc_init(void) { iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL); return 0; } subsys_initcall(blk_ioc_init);
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM libata #if !defined(_TRACE_LIBATA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LIBATA_H #include <linux/ata.h> #include <linux/libata.h> #include <linux/tracepoint.h> #include <linux/trace_seq.h> #define ata_opcode_name(opcode) { opcode, #opcode } #define show_opcode_name(val) \ __print_symbolic(val, \ ata_opcode_name(ATA_CMD_DEV_RESET), \ ata_opcode_name(ATA_CMD_CHK_POWER), \ ata_opcode_name(ATA_CMD_STANDBY), \ ata_opcode_name(ATA_CMD_IDLE), \ ata_opcode_name(ATA_CMD_EDD), \ ata_opcode_name(ATA_CMD_DOWNLOAD_MICRO), \ ata_opcode_name(ATA_CMD_DOWNLOAD_MICRO_DMA), \ ata_opcode_name(ATA_CMD_NOP), \ ata_opcode_name(ATA_CMD_FLUSH), \ ata_opcode_name(ATA_CMD_FLUSH_EXT), \ ata_opcode_name(ATA_CMD_ID_ATA), \ ata_opcode_name(ATA_CMD_ID_ATAPI), \ ata_opcode_name(ATA_CMD_SERVICE), \ ata_opcode_name(ATA_CMD_READ), \ ata_opcode_name(ATA_CMD_READ_EXT), \ ata_opcode_name(ATA_CMD_READ_QUEUED), \ ata_opcode_name(ATA_CMD_READ_STREAM_EXT), \ ata_opcode_name(ATA_CMD_READ_STREAM_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE), \ ata_opcode_name(ATA_CMD_WRITE_EXT), \ ata_opcode_name(ATA_CMD_WRITE_QUEUED), \ ata_opcode_name(ATA_CMD_WRITE_STREAM_EXT), \ ata_opcode_name(ATA_CMD_WRITE_STREAM_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_FUA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_QUEUED_FUA_EXT), \ ata_opcode_name(ATA_CMD_FPDMA_READ), \ ata_opcode_name(ATA_CMD_FPDMA_WRITE), \ ata_opcode_name(ATA_CMD_NCQ_NON_DATA), \ ata_opcode_name(ATA_CMD_FPDMA_SEND), \ ata_opcode_name(ATA_CMD_FPDMA_RECV), \ ata_opcode_name(ATA_CMD_PIO_READ), \ ata_opcode_name(ATA_CMD_PIO_READ_EXT), \ ata_opcode_name(ATA_CMD_PIO_WRITE), \ ata_opcode_name(ATA_CMD_PIO_WRITE_EXT), \ ata_opcode_name(ATA_CMD_READ_MULTI), \ ata_opcode_name(ATA_CMD_READ_MULTI_EXT), \ ata_opcode_name(ATA_CMD_WRITE_MULTI), \ ata_opcode_name(ATA_CMD_WRITE_MULTI_EXT), \ ata_opcode_name(ATA_CMD_WRITE_MULTI_FUA_EXT), \ ata_opcode_name(ATA_CMD_SET_FEATURES), \ ata_opcode_name(ATA_CMD_SET_MULTI), \ ata_opcode_name(ATA_CMD_PACKET), \ ata_opcode_name(ATA_CMD_VERIFY), \ ata_opcode_name(ATA_CMD_VERIFY_EXT), \ ata_opcode_name(ATA_CMD_WRITE_UNCORR_EXT), \ ata_opcode_name(ATA_CMD_STANDBYNOW1), \ ata_opcode_name(ATA_CMD_IDLEIMMEDIATE), \ ata_opcode_name(ATA_CMD_SLEEP), \ ata_opcode_name(ATA_CMD_INIT_DEV_PARAMS), \ ata_opcode_name(ATA_CMD_READ_NATIVE_MAX), \ ata_opcode_name(ATA_CMD_READ_NATIVE_MAX_EXT), \ ata_opcode_name(ATA_CMD_SET_MAX), \ ata_opcode_name(ATA_CMD_SET_MAX_EXT), \ ata_opcode_name(ATA_CMD_READ_LOG_EXT), \ ata_opcode_name(ATA_CMD_WRITE_LOG_EXT), \ ata_opcode_name(ATA_CMD_READ_LOG_DMA_EXT), \ ata_opcode_name(ATA_CMD_WRITE_LOG_DMA_EXT), \ ata_opcode_name(ATA_CMD_TRUSTED_NONDATA), \ ata_opcode_name(ATA_CMD_TRUSTED_RCV), \ ata_opcode_name(ATA_CMD_TRUSTED_RCV_DMA), \ ata_opcode_name(ATA_CMD_TRUSTED_SND), \ ata_opcode_name(ATA_CMD_TRUSTED_SND_DMA), \ ata_opcode_name(ATA_CMD_PMP_READ), \ ata_opcode_name(ATA_CMD_PMP_READ_DMA), \ ata_opcode_name(ATA_CMD_PMP_WRITE), \ ata_opcode_name(ATA_CMD_PMP_WRITE_DMA), \ ata_opcode_name(ATA_CMD_CONF_OVERLAY), \ ata_opcode_name(ATA_CMD_SEC_SET_PASS), \ ata_opcode_name(ATA_CMD_SEC_UNLOCK), \ ata_opcode_name(ATA_CMD_SEC_ERASE_PREP), \ ata_opcode_name(ATA_CMD_SEC_ERASE_UNIT), \ ata_opcode_name(ATA_CMD_SEC_FREEZE_LOCK), \ ata_opcode_name(ATA_CMD_SEC_DISABLE_PASS), \ ata_opcode_name(ATA_CMD_CONFIG_STREAM), \ ata_opcode_name(ATA_CMD_SMART), \ ata_opcode_name(ATA_CMD_MEDIA_LOCK), \ ata_opcode_name(ATA_CMD_MEDIA_UNLOCK), \ ata_opcode_name(ATA_CMD_DSM), \ ata_opcode_name(ATA_CMD_CHK_MED_CRD_TYP), \ ata_opcode_name(ATA_CMD_CFA_REQ_EXT_ERR), \ ata_opcode_name(ATA_CMD_CFA_WRITE_NE), \ ata_opcode_name(ATA_CMD_CFA_TRANS_SECT), \ ata_opcode_name(ATA_CMD_CFA_ERASE), \ ata_opcode_name(ATA_CMD_CFA_WRITE_MULT_NE), \ ata_opcode_name(ATA_CMD_REQ_SENSE_DATA), \ ata_opcode_name(ATA_CMD_SANITIZE_DEVICE), \ ata_opcode_name(ATA_CMD_ZAC_MGMT_IN), \ ata_opcode_name(ATA_CMD_ZAC_MGMT_OUT), \ ata_opcode_name(ATA_CMD_RESTORE), \ ata_opcode_name(ATA_CMD_READ_LONG), \ ata_opcode_name(ATA_CMD_READ_LONG_ONCE), \ ata_opcode_name(ATA_CMD_WRITE_LONG), \ ata_opcode_name(ATA_CMD_WRITE_LONG_ONCE)) #define ata_error_name(result) { result, #result } #define show_error_name(val) \ __print_symbolic(val, \ ata_error_name(ATA_ICRC), \ ata_error_name(ATA_UNC), \ ata_error_name(ATA_MC), \ ata_error_name(ATA_IDNF), \ ata_error_name(ATA_MCR), \ ata_error_name(ATA_ABORTED), \ ata_error_name(ATA_TRK0NF), \ ata_error_name(ATA_AMNF)) #define ata_protocol_name(proto) { proto, #proto } #define show_protocol_name(val) \ __print_symbolic(val, \ ata_protocol_name(ATA_PROT_UNKNOWN), \ ata_protocol_name(ATA_PROT_NODATA), \ ata_protocol_name(ATA_PROT_PIO), \ ata_protocol_name(ATA_PROT_DMA), \ ata_protocol_name(ATA_PROT_NCQ), \ ata_protocol_name(ATA_PROT_NCQ_NODATA), \ ata_protocol_name(ATAPI_PROT_NODATA), \ ata_protocol_name(ATAPI_PROT_PIO), \ ata_protocol_name(ATAPI_PROT_DMA)) const char *libata_trace_parse_status(struct trace_seq*, unsigned char); #define __parse_status(s) libata_trace_parse_status(p, s) const char *libata_trace_parse_eh_action(struct trace_seq *, unsigned int); #define __parse_eh_action(a) libata_trace_parse_eh_action(p, a) const char *libata_trace_parse_eh_err_mask(struct trace_seq *, unsigned int); #define __parse_eh_err_mask(m) libata_trace_parse_eh_err_mask(p, m) const char *libata_trace_parse_qc_flags(struct trace_seq *, unsigned int); #define __parse_qc_flags(f) libata_trace_parse_qc_flags(p, f) const char *libata_trace_parse_subcmd(struct trace_seq *, unsigned char, unsigned char, unsigned char); #define __parse_subcmd(c,f,h) libata_trace_parse_subcmd(p, c, f, h) TRACE_EVENT(ata_qc_issue, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned char, cmd ) __field( unsigned char, dev ) __field( unsigned char, lbal ) __field( unsigned char, lbam ) __field( unsigned char, lbah ) __field( unsigned char, nsect ) __field( unsigned char, feature ) __field( unsigned char, hob_lbal ) __field( unsigned char, hob_lbam ) __field( unsigned char, hob_lbah ) __field( unsigned char, hob_nsect ) __field( unsigned char, hob_feature ) __field( unsigned char, ctl ) __field( unsigned char, proto ) __field( unsigned long, flags ) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->proto = qc->tf.protocol; __entry->cmd = qc->tf.command; __entry->dev = qc->tf.device; __entry->lbal = qc->tf.lbal; __entry->lbam = qc->tf.lbam; __entry->lbah = qc->tf.lbah; __entry->hob_lbal = qc->tf.hob_lbal; __entry->hob_lbam = qc->tf.hob_lbam; __entry->hob_lbah = qc->tf.hob_lbah; __entry->feature = qc->tf.feature; __entry->hob_feature = qc->tf.hob_feature; __entry->nsect = qc->tf.nsect; __entry->hob_nsect = qc->tf.hob_nsect; ), TP_printk("ata_port=%u ata_dev=%u tag=%d proto=%s cmd=%s%s " \ " tf=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", __entry->ata_port, __entry->ata_dev, __entry->tag, show_protocol_name(__entry->proto), show_opcode_name(__entry->cmd), __parse_subcmd(__entry->cmd, __entry->feature, __entry->hob_nsect), __entry->cmd, __entry->feature, __entry->nsect, __entry->lbal, __entry->lbam, __entry->lbah, __entry->hob_feature, __entry->hob_nsect, __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, __entry->dev) ); DECLARE_EVENT_CLASS(ata_qc_complete_template, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned char, status ) __field( unsigned char, dev ) __field( unsigned char, lbal ) __field( unsigned char, lbam ) __field( unsigned char, lbah ) __field( unsigned char, nsect ) __field( unsigned char, error ) __field( unsigned char, hob_lbal ) __field( unsigned char, hob_lbam ) __field( unsigned char, hob_lbah ) __field( unsigned char, hob_nsect ) __field( unsigned char, hob_feature ) __field( unsigned char, ctl ) __field( unsigned long, flags ) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->status = qc->result_tf.command; __entry->dev = qc->result_tf.device; __entry->lbal = qc->result_tf.lbal; __entry->lbam = qc->result_tf.lbam; __entry->lbah = qc->result_tf.lbah; __entry->hob_lbal = qc->result_tf.hob_lbal; __entry->hob_lbam = qc->result_tf.hob_lbam; __entry->hob_lbah = qc->result_tf.hob_lbah; __entry->error = qc->result_tf.feature; __entry->hob_feature = qc->result_tf.hob_feature; __entry->nsect = qc->result_tf.nsect; __entry->hob_nsect = qc->result_tf.hob_nsect; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s status=%s " \ " res=(%02x/%02x:%02x:%02x:%02x:%02x/%02x:%02x:%02x:%02x:%02x/%02x)", __entry->ata_port, __entry->ata_dev, __entry->tag, __parse_qc_flags(__entry->flags), __parse_status(__entry->status), __entry->status, __entry->error, __entry->nsect, __entry->lbal, __entry->lbam, __entry->lbah, __entry->hob_feature, __entry->hob_nsect, __entry->hob_lbal, __entry->hob_lbam, __entry->hob_lbah, __entry->dev) ); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_internal, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_failed, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); DEFINE_EVENT(ata_qc_complete_template, ata_qc_complete_done, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc)); TRACE_EVENT(ata_eh_link_autopsy, TP_PROTO(struct ata_device *dev, unsigned int eh_action, unsigned int eh_err_mask), TP_ARGS(dev, eh_action, eh_err_mask), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, eh_action ) __field( unsigned int, eh_err_mask) ), TP_fast_assign( __entry->ata_port = dev->link->ap->print_id; __entry->ata_dev = dev->link->pmp + dev->devno; __entry->eh_action = eh_action; __entry->eh_err_mask = eh_err_mask; ), TP_printk("ata_port=%u ata_dev=%u eh_action=%s err_mask=%s", __entry->ata_port, __entry->ata_dev, __parse_eh_action(__entry->eh_action), __parse_eh_err_mask(__entry->eh_err_mask)) ); TRACE_EVENT(ata_eh_link_autopsy_qc, TP_PROTO(struct ata_queued_cmd *qc), TP_ARGS(qc), TP_STRUCT__entry( __field( unsigned int, ata_port ) __field( unsigned int, ata_dev ) __field( unsigned int, tag ) __field( unsigned int, qc_flags ) __field( unsigned int, eh_err_mask) ), TP_fast_assign( __entry->ata_port = qc->ap->print_id; __entry->ata_dev = qc->dev->link->pmp + qc->dev->devno; __entry->tag = qc->tag; __entry->qc_flags = qc->flags; __entry->eh_err_mask = qc->err_mask; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s err_mask=%s", __entry->ata_port, __entry->ata_dev, __entry->tag, __parse_qc_flags(__entry->qc_flags), __parse_eh_err_mask(__entry->eh_err_mask)) ); #endif /* _TRACE_LIBATA_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name, root->name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, id ) __field( int, level ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); ), TP_printk("root=%d id=%d level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_id ) __field( int, dst_level ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path, path); __entry->pid = task->pid; __assign_str(comm, task->comm); ), TP_printk("dst_root=%d dst_id=%d dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, id ) __field( int, level ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); __entry->val = val; ), TP_printk("root=%d id=%d level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 /* SPDX-License-Identifier: GPL-2.0-only */ /* * IEEE802.15.4-2003 specification * * Copyright (C) 2007, 2008 Siemens AG * * Written by: * Pavel Smolenskiy <pavel.smolenskiy@gmail.com> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Maxim Osipov <maxim.osipov@siemens.com> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #ifndef LINUX_IEEE802154_H #define LINUX_IEEE802154_H #include <linux/types.h> #include <linux/random.h> #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 #define IEEE802154_MAX_AUTH_TAG_LEN 16 #define IEEE802154_FC_LEN 2 #define IEEE802154_SEQ_LEN 1 /* General MAC frame format: * 2 bytes: Frame Control * 1 byte: Sequence Number * 20 bytes: Addressing fields * 14 bytes: Auxiliary Security Header */ #define IEEE802154_MAX_HEADER_LEN (2 + 1 + 20 + 14) #define IEEE802154_MIN_HEADER_LEN (IEEE802154_ACK_PSDU_LEN - \ IEEE802154_FCS_LEN) #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_UNSPEC 0xfffe #define IEEE802154_EXTENDED_ADDR_LEN 8 #define IEEE802154_SHORT_ADDR_LEN 2 #define IEEE802154_PAN_ID_LEN 2 #define IEEE802154_LIFS_PERIOD 40 #define IEEE802154_SIFS_PERIOD 12 #define IEEE802154_MAX_SIFS_FRAME_SIZE 18 #define IEEE802154_MAX_CHANNEL 26 #define IEEE802154_MAX_PAGE 31 #define IEEE802154_FC_TYPE_BEACON 0x0 /* Frame is beacon */ #define IEEE802154_FC_TYPE_DATA 0x1 /* Frame is data */ #define IEEE802154_FC_TYPE_ACK 0x2 /* Frame is acknowledgment */ #define IEEE802154_FC_TYPE_MAC_CMD 0x3 /* Frame is MAC command */ #define IEEE802154_FC_TYPE_SHIFT 0 #define IEEE802154_FC_TYPE_MASK ((1 << 3) - 1) #define IEEE802154_FC_TYPE(x) ((x & IEEE802154_FC_TYPE_MASK) >> IEEE802154_FC_TYPE_SHIFT) #define IEEE802154_FC_SET_TYPE(v, x) do { \ v = (((v) & ~IEEE802154_FC_TYPE_MASK) | \ (((x) << IEEE802154_FC_TYPE_SHIFT) & IEEE802154_FC_TYPE_MASK)); \ } while (0) #define IEEE802154_FC_SECEN_SHIFT 3 #define IEEE802154_FC_SECEN (1 << IEEE802154_FC_SECEN_SHIFT) #define IEEE802154_FC_FRPEND_SHIFT 4 #define IEEE802154_FC_FRPEND (1 << IEEE802154_FC_FRPEND_SHIFT) #define IEEE802154_FC_ACK_REQ_SHIFT 5 #define IEEE802154_FC_ACK_REQ (1 << IEEE802154_FC_ACK_REQ_SHIFT) #define IEEE802154_FC_INTRA_PAN_SHIFT 6 #define IEEE802154_FC_INTRA_PAN (1 << IEEE802154_FC_INTRA_PAN_SHIFT) #define IEEE802154_FC_SAMODE_SHIFT 14 #define IEEE802154_FC_SAMODE_MASK (3 << IEEE802154_FC_SAMODE_SHIFT) #define IEEE802154_FC_DAMODE_SHIFT 10 #define IEEE802154_FC_DAMODE_MASK (3 << IEEE802154_FC_DAMODE_SHIFT) #define IEEE802154_FC_VERSION_SHIFT 12 #define IEEE802154_FC_VERSION_MASK (3 << IEEE802154_FC_VERSION_SHIFT) #define IEEE802154_FC_VERSION(x) ((x & IEEE802154_FC_VERSION_MASK) >> IEEE802154_FC_VERSION_SHIFT) #define IEEE802154_FC_SAMODE(x) \ (((x) & IEEE802154_FC_SAMODE_MASK) >> IEEE802154_FC_SAMODE_SHIFT) #define IEEE802154_FC_DAMODE(x) \ (((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT) #define IEEE802154_SCF_SECLEVEL_MASK 7 #define IEEE802154_SCF_SECLEVEL_SHIFT 0 #define IEEE802154_SCF_SECLEVEL(x) (x & IEEE802154_SCF_SECLEVEL_MASK) #define IEEE802154_SCF_KEY_ID_MODE_SHIFT 3 #define IEEE802154_SCF_KEY_ID_MODE_MASK (3 << IEEE802154_SCF_KEY_ID_MODE_SHIFT) #define IEEE802154_SCF_KEY_ID_MODE(x) \ ((x & IEEE802154_SCF_KEY_ID_MODE_MASK) >> IEEE802154_SCF_KEY_ID_MODE_SHIFT) #define IEEE802154_SCF_KEY_IMPLICIT 0 #define IEEE802154_SCF_KEY_INDEX 1 #define IEEE802154_SCF_KEY_SHORT_INDEX 2 #define IEEE802154_SCF_KEY_HW_INDEX 3 #define IEEE802154_SCF_SECLEVEL_NONE 0 #define IEEE802154_SCF_SECLEVEL_MIC32 1 #define IEEE802154_SCF_SECLEVEL_MIC64 2 #define IEEE802154_SCF_SECLEVEL_MIC128 3 #define IEEE802154_SCF_SECLEVEL_ENC 4 #define IEEE802154_SCF_SECLEVEL_ENC_MIC32 5 #define IEEE802154_SCF_SECLEVEL_ENC_MIC64 6 #define IEEE802154_SCF_SECLEVEL_ENC_MIC128 7 /* MAC footer size */ #define IEEE802154_MFR_SIZE 2 /* 2 octets */ /* MAC's Command Frames Identifiers */ #define IEEE802154_CMD_ASSOCIATION_REQ 0x01 #define IEEE802154_CMD_ASSOCIATION_RESP 0x02 #define IEEE802154_CMD_DISASSOCIATION_NOTIFY 0x03 #define IEEE802154_CMD_DATA_REQ 0x04 #define IEEE802154_CMD_PANID_CONFLICT_NOTIFY 0x05 #define IEEE802154_CMD_ORPHAN_NOTIFY 0x06 #define IEEE802154_CMD_BEACON_REQ 0x07 #define IEEE802154_CMD_COORD_REALIGN_NOTIFY 0x08 #define IEEE802154_CMD_GTS_REQ 0x09 /* * The return values of MAC operations */ enum { /* * The requested operation was completed successfully. * For a transmission request, this value indicates * a successful transmission. */ IEEE802154_SUCCESS = 0x0, /* The beacon was lost following a synchronization request. */ IEEE802154_BEACON_LOSS = 0xe0, /* * A transmission could not take place due to activity on the * channel, i.e., the CSMA-CA mechanism has failed. */ IEEE802154_CHNL_ACCESS_FAIL = 0xe1, /* The GTS request has been denied by the PAN coordinator. */ IEEE802154_DENINED = 0xe2, /* The attempt to disable the transceiver has failed. */ IEEE802154_DISABLE_TRX_FAIL = 0xe3, /* * The received frame induces a failed security check according to * the security suite. */ IEEE802154_FAILED_SECURITY_CHECK = 0xe4, /* * The frame resulting from secure processing has a length that is * greater than aMACMaxFrameSize. */ IEEE802154_FRAME_TOO_LONG = 0xe5, /* * The requested GTS transmission failed because the specified GTS * either did not have a transmit GTS direction or was not defined. */ IEEE802154_INVALID_GTS = 0xe6, /* * A request to purge an MSDU from the transaction queue was made using * an MSDU handle that was not found in the transaction table. */ IEEE802154_INVALID_HANDLE = 0xe7, /* A parameter in the primitive is out of the valid range.*/ IEEE802154_INVALID_PARAMETER = 0xe8, /* No acknowledgment was received after aMaxFrameRetries. */ IEEE802154_NO_ACK = 0xe9, /* A scan operation failed to find any network beacons.*/ IEEE802154_NO_BEACON = 0xea, /* No response data were available following a request. */ IEEE802154_NO_DATA = 0xeb, /* The operation failed because a short address was not allocated. */ IEEE802154_NO_SHORT_ADDRESS = 0xec, /* * A receiver enable request was unsuccessful because it could not be * completed within the CAP. */ IEEE802154_OUT_OF_CAP = 0xed, /* * A PAN identifier conflict has been detected and communicated to the * PAN coordinator. */ IEEE802154_PANID_CONFLICT = 0xee, /* A coordinator realignment command has been received. */ IEEE802154_REALIGMENT = 0xef, /* The transaction has expired and its information discarded. */ IEEE802154_TRANSACTION_EXPIRED = 0xf0, /* There is no capacity to store the transaction. */ IEEE802154_TRANSACTION_OVERFLOW = 0xf1, /* * The transceiver was in the transmitter enabled state when the * receiver was requested to be enabled. */ IEEE802154_TX_ACTIVE = 0xf2, /* The appropriate key is not available in the ACL. */ IEEE802154_UNAVAILABLE_KEY = 0xf3, /* * A SET/GET request was issued with the identifier of a PIB attribute * that is not supported. */ IEEE802154_UNSUPPORTED_ATTR = 0xf4, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. */ IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; /* frame control handling */ #define IEEE802154_FCTL_FTYPE 0x0003 #define IEEE802154_FCTL_ACKREQ 0x0020 #define IEEE802154_FCTL_SECEN 0x0004 #define IEEE802154_FCTL_INTRA_PAN 0x0040 #define IEEE802154_FCTL_DADDR 0x0c00 #define IEEE802154_FCTL_SADDR 0xc000 #define IEEE802154_FTYPE_DATA 0x0001 #define IEEE802154_FCTL_ADDR_NONE 0x0000 #define IEEE802154_FCTL_DADDR_SHORT 0x0800 #define IEEE802154_FCTL_DADDR_EXTENDED 0x0c00 #define IEEE802154_FCTL_SADDR_SHORT 0x8000 #define IEEE802154_FCTL_SADDR_EXTENDED 0xc000 /* * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ static inline int ieee802154_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == cpu_to_le16(IEEE802154_FTYPE_DATA); } /** * ieee802154_is_secen - check if Security bit is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_secen(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_SECEN); } /** * ieee802154_is_ackreq - check if acknowledgment request bit is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_ackreq(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_ACKREQ); } /** * ieee802154_is_intra_pan - check if intra pan id communication * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_intra_pan(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); } /* * ieee802154_daddr_mode - get daddr mode from fc * @fc: frame control bytes in little-endian byteorder */ static inline __le16 ieee802154_daddr_mode(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_DADDR); } /* * ieee802154_saddr_mode - get saddr mode from fc * @fc: frame control bytes in little-endian byteorder */ static inline __le16 ieee802154_saddr_mode(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_SADDR); } /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: * 0-4 Reserved * 5 MPDU (Acknowledgment) * 6-8 Reserved * 9-127 MPDU * * @len: psdu len with (MHR + payload + MFR) */ static inline bool ieee802154_is_valid_psdu_len(u8 len) { return (len == IEEE802154_ACK_PSDU_LEN || (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU)); } /** * ieee802154_is_valid_extended_unicast_addr - check if extended addr is valid * @addr: extended addr to check */ static inline bool ieee802154_is_valid_extended_unicast_addr(__le64 addr) { /* Bail out if the address is all zero, or if the group * address bit is set. */ return ((addr != cpu_to_le64(0x0000000000000000ULL)) && !(addr & cpu_to_le64(0x0100000000000000ULL))); } /** * ieee802154_is_broadcast_short_addr - check if short addr is broadcast * @addr: short addr to check */ static inline bool ieee802154_is_broadcast_short_addr(__le16 addr) { return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)); } /** * ieee802154_is_unspec_short_addr - check if short addr is unspecified * @addr: short addr to check */ static inline bool ieee802154_is_unspec_short_addr(__le16 addr) { return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC)); } /** * ieee802154_is_valid_src_short_addr - check if source short address is valid * @addr: short addr to check */ static inline bool ieee802154_is_valid_src_short_addr(__le16 addr) { return !(ieee802154_is_broadcast_short_addr(addr) || ieee802154_is_unspec_short_addr(addr)); } /** * ieee802154_random_extended_addr - generates a random extended address * @addr: extended addr pointer to place the random address */ static inline void ieee802154_random_extended_addr(__le64 *addr) { get_random_bytes(addr, IEEE802154_EXTENDED_ADDR_LEN); /* clear the group bit, and set the locally administered bit */ ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] &= ~0x01; ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] |= 0x02; } #endif /* LINUX_IEEE802154_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ #include <linux/efi.h> /* efi_recover_from_page_fault()*/ #include <linux/mm_types.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> /* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) return -1; return 0; } /* * Prefetch quirks: * * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * * Sometimes the CPU reports invalid exceptions on prefetch. * Check that here and ignore it. * * Opcode checker based on code by Richard Brunner. */ static inline int check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, unsigned char opcode, int *prefetch) { unsigned char instr_hi = opcode & 0xf0; unsigned char instr_lo = opcode & 0x0f; switch (instr_hi) { case 0x20: case 0x30: /* * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. * In X86_64 long mode, the CPU will signal invalid * opcode if some of these prefixes are present so * X86_64 will never get here anyway */ return ((instr_lo & 7) == 0x6); #ifdef CONFIG_X86_64 case 0x40: /* * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif case 0x60: /* 0x64 thru 0x67 are valid prefixes in all modes. */ return (instr_lo & 0xC) == 0x4; case 0xF0: /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */ return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && (opcode == 0x0D || opcode == 0x18); return 0; default: return 0; } } static int is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) { unsigned char *max_instr; unsigned char *instr; int prefetch = 0; /* * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; /* * This code has historically always bailed out if IP points to a * not-present page (e.g. due to a race). No one has ever * complained about this. */ pagefault_disable(); while (instr < max_instr) { unsigned char opcode; if (user_mode(regs)) { if (get_user(opcode, instr)) break; } else { if (get_kernel_nofault(opcode, instr)) break; } instr++; if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } pagefault_enable(); return prefetch; } DEFINE_SPINLOCK(pgd_lock); LIST_HEAD(pgd_list); #ifdef CONFIG_X86_32 static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; pgd += index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) return NULL; /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would * set_p4d/set_pud. */ p4d = p4d_offset(pgd, address); p4d_k = p4d_offset(pgd_k, address); if (!p4d_present(*p4d_k)) return NULL; pud = pud_offset(p4d, address); pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); if (!pmd_present(*pmd_k)) return NULL; else BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } /* * Handle a fault on the vmalloc or module mapping area * * This is needed because there is a race condition between the time * when the vmalloc mapping code updates the PMD to the point in time * where it synchronizes this update with the other page-tables in the * system. * * In this race window another thread/CPU can map an area on the same * PMD, finds it already present and does not synchronize it with the * rest of the system yet. As a result v[mz]alloc might return areas * which are not mapped in every page-table in the system, causing an * unhandled page-fault when they are accessed. */ static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; /* Make sure we are in vmalloc area: */ if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; /* * Synchronize this task's top level page-table * with the 'reference' page table. * * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; if (pmd_large(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; return 0; } NOKPROBE_SYMBOL(vmalloc_fault); void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start & PMD_MASK; addr >= TASK_SIZE_MAX && addr < VMALLOC_END; addr += PMD_SIZE) { struct page *page; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); vmalloc_sync_one(page_address(page), addr); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } /* * Did it hit the DOS screen memory VA from vm86 mode? */ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { #ifdef CONFIG_VM86 unsigned long bit; if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) tsk->thread.vm86->screen_bitmap |= 1 << bit; #endif } static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; #ifdef CONFIG_X86_PAE pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #define pr_pde pr_cont #else #define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); #undef pr_pde /* * We must not directly access the pte in the highpte * case if the page table is located in highmem. * And let's rather not kmap-atomic the pte, just in case * it's allocated already: */ if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: pr_cont("\n"); } #else /* CONFIG_X86_64: */ #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" "******* Working around it, but it may cause SEGVs or burn power.\n" "******* Please consider a BIOS update.\n" "******* Disabling USB legacy in the BIOS may also help.\n"; #endif /* * No vm86 mode in 64-bit mode: */ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { } static int bad_address(void *p) { unsigned long dummy; return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; if (bad_address(pgd)) goto bad; pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (bad_address(p4d)) goto bad; pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_large(*p4d)) goto out; pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_large(*pud)) goto out; pmd = pmd_offset(pud, address); if (bad_address(pmd)) goto bad; pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_large(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); if (bad_address(pte)) goto bad; pr_cont("PTE %lx", pte_val(*pte)); out: pr_cont("\n"); return; bad: pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ /* * Workaround for K8 erratum #93 & buggy BIOS. * * BIOS SMM functions are required to use a specific workaround * to avoid corruption of the 64bit RIP register on C stepping K8. * * A lot of BIOS that didn't get tested properly miss this. * * The OS sees this as a page fault with the upper 32bits of RIP cleared. * Try to work around it here. * * Note we only handle faults in kernel here. * Does nothing on 32-bit. */ static int is_errata93(struct pt_regs *regs, unsigned long address) { #if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD || boot_cpu_data.x86 != 0xf) return 0; if (address != regs->ip) return 0; if ((address >> 32) != 0) return 0; address |= 0xffffffffUL << 32; if ((address >= (u64)_stext && address <= (u64)_etext) || (address >= MODULES_VADDR && address <= MODULES_END)) { printk_once(errata93_warning); regs->ip = address; return 1; } #endif return 0; } /* * Work around K8 erratum #100 K8 in compat mode occasionally jumps * to illegal addresses >4GB. * * We catch this in the page fault handler because these addresses * are not reachable. Just detect this case and return. Any code * segment in LDT is compatibility mode. */ static int is_errata100(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_64 if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32)) return 1; #endif return 0; } /* Pentium F0 0F C7 C8 bug workaround: */ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_F00F_BUG if (boot_cpu_has_bug(X86_BUG_F00F) && idt_is_f00f_address(address)) { handle_invalid_op(regs); return 1; } #endif return 0; } static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) { u32 offset = (index >> 3) * sizeof(struct desc_struct); unsigned long addr; struct ldttss_desc desc; if (index == 0) { pr_alert("%s: NULL\n", name); return; } if (offset + sizeof(struct ldttss_desc) >= gdt->size) { pr_alert("%s: 0x%hx -- out of bounds\n", name, index); return; } if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); return; } addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n", name, index, addr, (desc.limit0 | (desc.limit1 << 16))); } static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!oops_may_print()) return; if (error_code & X86_PF_INSTR) { unsigned int level; pgd_t *pgd; pte_t *pte; pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); if (pte && pte_present(*pte) && pte_exec(*pte) && (pgd_flags(*pgd) & _PAGE_USER) && (__read_cr4() & X86_CR4_SMEP)) pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); } if (address < PAGE_SIZE && !user_mode(regs)) pr_alert("BUG: kernel NULL pointer dereference, address: %px\n", (void *)address); else pr_alert("BUG: unable to handle page fault for address: %px\n", (void *)address); pr_alert("#PF: %s %s in %s mode\n", (error_code & X86_PF_USER) ? "user" : "supervisor", (error_code & X86_PF_INSTR) ? "instruction fetch" : (error_code & X86_PF_WRITE) ? "write access" : "read access", user_mode(regs) ? "user" : "kernel"); pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code, !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { struct desc_ptr idt, gdt; u16 ldtr, tr; /* * This can happen for quite a few reasons. The more obvious * ones are faults accessing the GDT, or LDT. Perhaps * surprisingly, if the CPU tries to deliver a benign or * contributory exception from user code and gets a page fault * during delivery, the page fault can be delivered as though * it originated directly from user code. This could happen * due to wrong permissions on the IDT, GDT, LDT, TSS, or * kernel or IST stack. */ store_idt(&idt); /* Usable even on Xen PV -- it's just slow. */ native_store_gdt(&gdt); pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n", idt.address, idt.size, gdt.address, gdt.size); store_ldt(ldtr); show_ldttss(&gdt, "LDTR", ldtr); store_tr(tr); show_ldttss(&gdt, "TR", tr); } dump_pagetable(address); } static noinline void pgtable_bad(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct task_struct *tsk; unsigned long flags; int sig; flags = oops_begin(); tsk = current; sig = SIGKILL; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", tsk->comm, address); dump_pagetable(address); if (__die("Bad pagetable", regs, error_code)) sig = 0; oops_end(flags, regs, sig); } static void set_signal_archinfo(unsigned long address, unsigned long error_code) { struct task_struct *tsk = current; /* * To avoid leaking information about the kernel page * table layout, pretend that user-mode accesses to * kernel addresses are always protection faults. * * NB: This means that failed vsyscalls with vsyscall=none * will have the PROT bit. This doesn't leak any * information and does not appear to cause any problems. */ if (address >= TASK_SIZE_MAX) error_code |= X86_PF_PROT; tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; } static noinline void no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; unsigned long flags; int sig; if (user_mode(regs)) { /* * This is an implicit supervisor-mode access from user * mode. Bypass all the kernel-mode recovery code and just * OOPS. */ goto oops; } /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) { /* * Any interrupt that takes a fault gets the fixup. This makes * the below recursive fault logic only apply to a faults from * task context. */ if (in_interrupt()) return; /* * Per the above we're !in_interrupt(), aka. task context. * * In this case we need to make sure we're not recursively * faulting through the emulate_vsyscall() logic. */ if (current->thread.sig_on_uaccess_err && signal) { set_signal_archinfo(address, error_code); /* XXX: hwpoison faults will set the wrong code. */ force_sig_fault(signal, si_code, (void __user *)address); } /* * Barring that, we can do the fixup and be happy. */ return; } #ifdef CONFIG_VMAP_STACK /* * Stack overflow? During boot, we can fault near the initial * stack in the direct map, but that's not an overflow -- check * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *); /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but * double-fault even before we get this far, in which case * we're fine: the double-fault handler will deal with it. * * We don't want to make it all the way into the oops code * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ asm volatile ("movq %[stack], %%rsp\n\t" "call handle_stack_overflow\n\t" "1: jmp 1b" : ASM_CALL_CONSTRAINT : "D" ("kernel stack overflow (page fault)"), "S" (regs), "d" (address), [stack] "rm" (stack)); unreachable(); } #endif /* * 32-bit: * * Valid to do another page fault here, because if this fault * had been triggered by is_prefetch fixup_exception would have * handled it. * * 64-bit: * * Hall of shame of CPU/BIOS bugs. */ if (is_prefetch(regs, error_code, address)) return; if (is_errata93(regs, address)) return; /* * Buggy firmware could access regions which might page fault, try to * recover from such faults. */ if (IS_ENABLED(CONFIG_EFI)) efi_recover_from_page_fault(address); oops: /* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice: */ flags = oops_begin(); show_fault_oops(regs, error_code, address); if (task_stack_end_corrupted(tsk)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); sig = SIGKILL; if (__die("Oops", regs, error_code)) sig = 0; /* Executive summary in case the body of the oops scrolled away */ printk(KERN_DEFAULT "CR2: %016lx\n", address); oops_end(flags, regs, sig); } /* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: */ static inline void show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; if (!unhandled_signal(tsk, SIGSEGV)) return; if (!printk_ratelimit()) return; printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", loglvl, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); print_vma_addr(KERN_CONT " in ", regs->ip); printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); } /* * The (legacy) vsyscall page is the long page in the kernel portion * of the address space that has user-accessible permissions. */ static bool is_vsyscall_vaddr(unsigned long vaddr) { return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); } static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct task_struct *tsk = current; /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs) && (error_code & X86_PF_USER)) { /* * It's possible to have interrupts off here: */ local_irq_enable(); /* * Valid to do another page fault here because this one came * from user space: */ if (is_prefetch(regs, error_code, address)) return; if (is_errata100(regs, address)) return; /* * To avoid leaking information about the kernel page table * layout, pretend that user-mode accesses to kernel addresses * are always protection faults. */ if (address >= TASK_SIZE_MAX) error_code |= X86_PF_PROT; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); set_signal_archinfo(address, error_code); if (si_code == SEGV_PKUERR) force_sig_pkuerr((void __user *)address, pkey); force_sig_fault(SIGSEGV, si_code, (void __user *)address); local_irq_disable(); return; } if (is_f00f_bug(regs, address)) return; no_context(regs, error_code, address, SIGSEGV, si_code); } static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR); } static void __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ mmap_read_unlock(mm); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } static noinline void bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area(regs, error_code, address, 0, SEGV_MAPERR); } static inline bool bad_area_access_from_pkeys(unsigned long error_code, struct vm_area_struct *vma) { /* This code is always called on the current mm */ bool foreign = false; if (!boot_cpu_has(X86_FEATURE_OSPKE)) return false; if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return true; return false; } static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. * But, doing it this way allows compiler optimizations * if pkeys are compiled out. */ if (bad_area_access_from_pkeys(error_code, vma)) { /* * A protection key fault means that the PKRU value did not allow * access to some PTE. Userspace can figure out what PKRU was * from the XSAVE state. This function captures the pkey from * the vma and passes it to userspace so userspace can discover * which protection key was set on the PTE. * * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set PKRU to deny access to pkey=4, touches page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ u32 pkey = vma_pkey(vma); __bad_area(regs, error_code, address, pkey, SEGV_PKUERR); } else { __bad_area(regs, error_code, address, 0, SEGV_ACCERR); } } static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } /* User-space => ok to do another page fault: */ if (is_prefetch(regs, error_code, address)) return; set_signal_archinfo(address, error_code); #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { struct task_struct *tsk = current; unsigned lsb = 0; pr_err( "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n", tsk->comm, tsk->pid, address); if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); if (fault & VM_FAULT_HWPOISON) lsb = PAGE_SHIFT; force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb); return; } #endif force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { no_context(regs, error_code, address, 0, 0); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; } /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got * oom-killed): */ pagefault_out_of_memory(); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); else if (fault & VM_FAULT_SIGSEGV) bad_area_nosemaphore(regs, error_code, address); else BUG(); } } static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; return 1; } /* * Handle a spurious fault caused by a stale TLB entry. * * This allows us to lazily refresh the TLB when increasing the * permissions of a kernel page (RO -> RW or NX -> X). Doing it * eagerly is very expensive since that implies doing a full * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * * Spurious faults may only occur if the TLB contains an entry with * fewer permission than the page table entry. Non-present (P = 0) * and reserved bit (R = 1) faults are never spurious. * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. * * Returns non-zero if a spurious fault was handled, zero otherwise. * * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 * (Optional Invalidation). */ static noinline int spurious_kernel_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; int ret; /* * Only writes to RO or instruction fetches from NX may cause * spurious faults. * * These could be from user or supervisor accesses but the TLB * is only lazily flushed after a kernel mapping protection * change, so user accesses are not expected to cause spurious * faults. */ if (error_code != (X86_PF_WRITE | X86_PF_PROT) && error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); if (!pgd_present(*pgd)) return 0; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) return 0; if (p4d_large(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_large(*pmd)) return spurious_kernel_fault_check(error_code, (pte_t *) pmd); pte = pte_offset_kernel(pmd, address); if (!pte_present(*pte)) return 0; ret = spurious_kernel_fault_check(error_code, pte); if (!ret) return 0; /* * Make sure we have permissions in PMD. * If not, then there's a bug in the page tables: */ ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd); WARN_ONCE(!ret, "PMD has incorrect permission bits\n"); return ret; } NOKPROBE_SYMBOL(spurious_kernel_fault); int show_unhandled_signals = 1; static inline int access_error(unsigned long error_code, struct vm_area_struct *vma) { /* This is only called for the current mm, so: */ bool foreign = false; /* * Read or write was blocked by protection keys. This is * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ if (error_code & X86_PF_PK) return 1; /* * Make sure to check the VMA so that we do not perform * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return 1; if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } /* read, present: */ if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ if (unlikely(!vma_is_accessible(vma))) return 1; return 0; } bool fault_in_kernel_space(unsigned long address) { /* * On 64-bit systems, the vsyscall page is at an address above * TASK_SIZE_MAX, but is not considered part of the kernel * address space. */ if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address)) return false; return address >= TASK_SIZE_MAX; } /* * Called for all faults where 'address' is part of the kernel address * space. Might get called for faults that originate from *code* that * ran in userspace or the kernel. */ static void do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { /* * Protection keys exceptions only happen on user pages. We * have no user pages in the kernel portion of the address * space, so do not expect them here. */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); #ifdef CONFIG_X86_32 /* * We can fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. * * NOTE! We MUST NOT take any locks for this case. We may * be in an interrupt or a critical region, and should * only copy the information from the master page table, * nothing more. * * Before doing this on-demand faulting, ensure that the * fault is not any of the following: * 1. A fault on a PTE with a reserved bit set. * 2. A fault caused by a user-mode access. (Do not demand- * fault kernel memory due to user-mode accesses). * 3. A fault caused by a page-level protection violation. * (A demand fault would be on a non-present page which * would have X86_PF_PROT==0). * * This is only needed to close a race condition on x86-32 in * the vmalloc mapping/unmapping code. See the comment above * vmalloc_fault() for details. On x86-64 the race does not * exist as the vmalloc mappings don't need to be synchronized * there. */ if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; } #endif /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; /* kprobes don't want to hook the spurious faults: */ if (kprobe_page_fault(regs, X86_TRAP_PF)) return; /* * Note, despite being a "bad area", there are quite a few * acceptable reasons to get here, such as erratum fixups * and handling kernel code that can fault, like get_user(). * * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock: */ bad_area_nosemaphore(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_kern_addr_fault); /* Handle faults in the user portion of the address space */ static inline void do_user_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; /* kprobes don't want to hook the spurious faults: */ if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Reserved bits are never expected to be set on * entries in the user portion of the page tables. */ if (unlikely(hw_error_code & X86_PF_RSVD)) pgtable_bad(regs, hw_error_code, address); /* * If SMAP is on, check for invalid kernel (supervisor) access to user * pages in the user address space. The odd case here is WRUSS, * which, according to the preliminary documentation, does not respect * SMAP and will have the USER bit set so, in all cases, SMAP * enforcement appears to be consistent with the USER bit. */ if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) && !(hw_error_code & X86_PF_USER) && !(regs->flags & X86_EFLAGS_AC))) { bad_area_nosemaphore(regs, hw_error_code, address); return; } /* * If we're in an interrupt, have no user context or are running * in a region with pagefaults disabled then we must not take the fault */ if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, hw_error_code, address); return; } /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. * * User-mode registers count as a user access even for any * potential system fault or CPU buglet: */ if (user_mode(regs)) { local_irq_enable(); flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (hw_error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; if (hw_error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The * vsyscall page is at a high address (>PAGE_OFFSET), but is * considered to be part of the user address space. * * The vsyscall page does not have a "real" VMA, so do this * emulation before we go searching for VMAs. * * PKRU never rejects instruction fetches, so we don't need * to consider the PF_PK bit. */ if (is_vsyscall_vaddr(address)) { if (emulate_vsyscall(hw_error_code, regs, address)) return; } #endif /* * Kernel-mode access to the user address space should only occur * on well-defined single instructions listed in the exception * tables. But, an erroneous kernel fault occurring outside one of * those areas which also holds mmap_lock might deadlock attempting * to validate the fault against the address space. * * Only do the expensive exception table search when we might be at * risk of a deadlock. This happens if we * 1. Failed to acquire mmap_lock, and * 2. The access did not originate in userspace. */ if (unlikely(!mmap_read_trylock(mm))) { if (!user_mode(regs) && !search_exception_tables(regs->ip)) { /* * Fault from code in kernel from * which we do not expect faults. */ bad_area_nosemaphore(regs, hw_error_code, address); return; } retry: mmap_read_lock(mm); } else { /* * The above down_read_trylock() might have succeeded in * which case we'll have missed the might_sleep() from * down_read(): */ might_sleep(); } vma = find_vma(mm, address); if (unlikely(!vma)) { bad_area(regs, hw_error_code, address); return; } if (likely(vma->vm_start <= address)) goto good_area; if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { bad_area(regs, hw_error_code, address); return; } if (unlikely(expand_stack(vma, address))) { bad_area(regs, hw_error_code, address); return; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ good_area: if (unlikely(access_error(hw_error_code, vma))) { bad_area_access_error(regs, hw_error_code, address, vma); return; } /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked. * * Note that handle_userfault() may also release and reacquire mmap_lock * (and not return with VM_FAULT_RETRY), when returning to userland to * repeat the page fault later with a VM_FAULT_NOPAGE retval * (potentially after handling any pending signal during the return to * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) no_context(regs, hw_error_code, address, SIGBUS, BUS_ADRERR); return; } /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, hw_error_code, address, fault); return; } check_v8086_mode(regs, address, tsk); } NOKPROBE_SYMBOL(do_user_addr_fault); static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!trace_pagefault_enabled()) return; if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); else trace_page_fault_kernel(address, regs, error_code); } static __always_inline void handle_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { trace_page_fault_entries(regs, error_code, address); if (unlikely(kmmio_fault(regs, address))) return; /* Was the fault on kernel-controlled part of the address space? */ if (unlikely(fault_in_kernel_space(address))) { do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); /* * User address page fault handling might have reenabled * interrupts. Fixing up all potential exit points of * do_user_addr_fault() and its leaf functions is just not * doable w/o creating an unholy mess or turning the code * upside down. */ local_irq_disable(); } } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { unsigned long address = read_cr2(); irqentry_state_t state; prefetchw(&current->mm->mmap_lock); /* * KVM uses #PF vector to deliver 'page not present' events to guests * (asynchronous page fault mechanism). The event happens when a * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event * which is injected when the memory becomes available, is delived via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * * We are relying on the interrupted context being sane (valid RSP, * relevant locks not held, etc.), which is fine as long as the * interrupted context had IF=1. We are also relying on the KVM * async pf type field and CR2 being read consistently instead of * getting values from real and async page faults mixed up. * * Fingers crossed. * * The async #PF handling code takes care of idtentry handling * itself. */ if (kvm_handle_async_pf(regs, (u32)address)) return; /* * Entry handling for valid #PF from kernel mode is slightly * different: RCU is already watching and rcu_irq_enter() must not * be invoked because a kernel fault on a user space address might * sleep. * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps * debugability. */ state = irqentry_enter(regs); instrumentation_begin(); handle_page_fault(regs, error_code, address); instrumentation_end(); irqentry_exit(regs, state); }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H #include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); /** * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @pgprot: page protection to use * @write: whether it's a write fault * * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) { return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); } vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); /** * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @pgprot: page protection to use * @write: whether it's a write fault * * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) { return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); } enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_NEVER_DAX, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif }; struct kobject; struct kobj_attribute; ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) #define HPAGE_PUD_SHIFT PUD_SHIFT #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) extern unsigned long transparent_hugepage_flags; static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR)) return false; } if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, unsigned long vm_flags) { /* Explicitly disabled through madvise. */ if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; return true; } /* * to be used on vmas which are known to support THP. * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { /* * If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (vma_is_temporary_stack(vma)) return false; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; if (vma_is_dax(vma)) return true; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) return !!(vma->vm_flags & VM_HUGEPAGE); return false; } bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); bool is_transparent_hugepage(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ } while (0) void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ if (pud_trans_huge(*____pud) \ || pud_devmap(*____pud)) \ __split_huge_pud(__vma, __pud, __address); \ } while (0) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { return !pmd_none(pmd) && !pmd_present(pmd); } /* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } /** * thp_head - Head page of a transparent huge page. * @page: Any page (tail, head or regular) found in the page cache. */ static inline struct page *thp_head(struct page *page) { return compound_head(page); } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_ORDER; return 0; } /** * thp_nr_pages - The number of regular pages in this huge page. * @page: The head page of a huge page. */ static inline int thp_nr_pages(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_NR; return 1; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_page(struct page *page) { return READ_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); } static inline bool is_huge_zero_pud(pud_t pud) { return false; } struct page *mm_get_huge_zero_page(struct mm_struct *mm); void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } static inline struct list_head *page_deferred_list(struct page *page) { /* * Global or memcg deferred list in the second tail pages is * occupied by compound_head. */ return &page[2].deferred_list; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) static inline struct page *thp_head(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return page; } static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 0; } static inline int thp_nr_pages(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 1; } static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; } static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { return false; } static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, unsigned long vm_flags) { return false; } static inline void prep_transhuge_page(struct page *page) {} static inline bool is_transparent_hugepage(struct page *page) { return false; } #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool can_split_huge_page(struct page *page, int *pextra_pins) { BUILD_BUG(); return false; } static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { return 0; } static inline int split_huge_page(struct page *page) { return 0; } static inline void deferred_split_huge_page(struct page *page) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { BUG(); return 0; } static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { } static inline int is_swap_pmd(pmd_t pmd) { return 0; } static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { return NULL; } static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd) { return 0; } static inline bool is_huge_zero_page(struct page *page) { return false; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return false; } static inline bool is_huge_zero_pud(pud_t pud) { return false; } static inline void mm_put_huge_zero_page(struct mm_struct *mm) { return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline bool thp_migration_supported(void) { return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * * Return: Number of bytes in this page. */ static inline unsigned long thp_size(struct page *page) { return PAGE_SIZE << thp_order(page); } #endif /* _LINUX_HUGE_MM_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 /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash function */ int (*cmp)(const void *key1, const void *key2); /* key comparison function */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, int (*copy)(struct hashtab_node *new, struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #endif /* _SS_HASHTAB_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Filesystem parameter description and parser * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_FS_PARSER_H #define _LINUX_FS_PARSER_H #include <linux/fs_context.h> struct path; struct constant_table { const char *name; int value; }; struct fs_parameter_spec; struct fs_parse_result; typedef int fs_param_type(struct p_log *, const struct fs_parameter_spec *, struct fs_parameter *, struct fs_parse_result *); /* * The type of parameter expected. */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, fs_param_is_path, fs_param_is_fd; /* * Specification of the type of value a parameter wants. * * Note that the fsparam_flag(), fsparam_string(), fsparam_u32(), ... macros * should be used to generate elements of this type. */ struct fs_parameter_spec { const char *name; fs_param_type *type; /* The desired parameter type */ u8 opt; /* Option number (returned by fs_parse()) */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ const void *data; }; /* * Result of parse. */ struct fs_parse_result { bool negated; /* T if param was "noxxx" */ union { bool boolean; /* For spec_bool */ int int_32; /* For spec_s32/spec_enum */ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */ u64 uint_64; /* For spec_u64 */ }; }; extern int __fs_parse(struct p_log *log, const struct fs_parameter_spec *desc, struct fs_parameter *value, struct fs_parse_result *result); static inline int fs_parse(struct fs_context *fc, const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { return __fs_parse(&fc->log, desc, param, result); } extern int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, struct path *_path); extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); extern bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc); #else static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { return true; } static inline bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { return true; } #endif /* * Parameter type, name, index and flags element constructors. Use as: * * fsparam_xxxx("foo", Opt_foo) * * If existing helpers are not enough, direct use of __fsparam() would * work, but any such case is probably a sign that new helper is needed. * Helpers will remain stable; low-level implementation may change. */ #define __fsparam(TYPE, NAME, OPT, FLAGS, DATA) \ { \ .name = NAME, \ .opt = OPT, \ .type = TYPE, \ .flags = FLAGS, \ .data = DATA \ } #define fsparam_flag(NAME, OPT) __fsparam(NULL, NAME, OPT, 0, NULL) #define fsparam_flag_no(NAME, OPT) \ __fsparam(NULL, NAME, OPT, fs_param_neg_with_no, NULL) #define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0, NULL) #define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) #define fsparam_string(NAME, OPT) \ __fsparam(fs_param_is_string, NAME, OPT, 0, NULL) #define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0, NULL) #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) #endif /* _LINUX_FS_PARSER_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 /* * include/net/tipc.h: Include file for TIPC message header routines * * Copyright (c) 2017 Ericsson AB * 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 names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * 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. */ #ifndef _TIPC_HDR_H #define _TIPC_HDR_H #include <linux/random.h> #define KEEPALIVE_MSG_MASK 0x0e080000 /* LINK_PROTOCOL + MSG_IS_KEEPALIVE */ struct tipc_basic_hdr { __be32 w[4]; }; static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr) { u32 w0 = ntohl(hdr->w[0]); bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK; __be32 key; /* Return source node identity as key */ if (likely(!keepalive_msg)) return hdr->w[3]; /* Spread PROBE/PROBE_REPLY messages across the cores */ get_random_bytes(&key, sizeof(key)); return key; } #endif
1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #ifdef CONFIG_MEMCG_KMEM static LIST_HEAD(list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static void list_lru_register(struct list_lru *lru) { mutex_lock(&list_lrus_mutex); list_add(&lru->list, &list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) { struct list_lru_memcg *memcg_lrus; /* * Either lock or RCU protects the array of per cgroup lists * from relocation (see memcg_update_list_lru_node). */ memcg_lrus = rcu_dereference_check(nlru->memcg_lrus, lockdep_is_held(&nlru->lock)); if (memcg_lrus && idx >= 0) return memcg_lrus->lru[idx]; return &nlru->lru; } static inline struct list_lru_one * list_lru_from_kmem(struct list_lru_node *nlru, void *ptr, struct mem_cgroup **memcg_ptr) { struct list_lru_one *l = &nlru->lru; struct mem_cgroup *memcg = NULL; if (!nlru->memcg_lrus) goto out; memcg = mem_cgroup_from_obj(ptr); if (!memcg) goto out; l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); out: if (memcg_ptr) *memcg_ptr = memcg; return l; } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) { return &nlru->lru; } static inline struct list_lru_one * list_lru_from_kmem(struct list_lru_node *nlru, void *ptr, struct mem_cgroup **memcg_ptr) { if (memcg_ptr) *memcg_ptr = NULL; return &nlru->lru; } #endif /* CONFIG_MEMCG_KMEM */ bool list_lru_add(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; struct mem_cgroup *memcg; struct list_lru_one *l; spin_lock(&nlru->lock); if (list_empty(item)) { l = list_lru_from_kmem(nlru, item, &memcg); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) memcg_set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); nlru->nr_items++; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_del(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; spin_lock(&nlru->lock); if (!list_empty(item)) { l = list_lru_from_kmem(nlru, item, NULL); list_del_init(item); l->nr_items--; nlru->nr_items--; spin_unlock(&nlru->lock); return true; } spin_unlock(&nlru->lock); return false; } EXPORT_SYMBOL_GPL(list_lru_del); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; unsigned long count; rcu_read_lock(); l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); count = READ_ONCE(l->nr_items); rcu_read_unlock(); return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return nlru->nr_items; } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru_node *nlru, int memcg_idx, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; l = list_lru_from_memcg_idx(nlru, memcg_idx); restart: list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, &nlru->lock, cb_arg); switch (ret) { case LRU_REMOVED_RETRY: assert_spin_locked(&nlru->lock); fallthrough; case LRU_REMOVED: isolated++; nlru->nr_items--; /* * If the lru lock has been dropped, our list * traversal is now invalid and so we have to * restart from scratch. */ if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_RETRY: /* * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ assert_spin_locked(&nlru->lock); goto restart; default: BUG(); } } return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock(&nlru->lock); ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); return ret; } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { struct list_lru_node *nlru = &lru->node[nid]; unsigned long ret; spin_lock_irq(&nlru->lock); ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock_irq(&nlru->lock); return ret; } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; int memcg_idx; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { for_each_memcg_cache_index(memcg_idx) { struct list_lru_node *nlru = &lru->node[nid]; spin_lock(&nlru->lock); isolated += __list_lru_walk_one(nlru, memcg_idx, isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); if (*nr_to_walk <= 0) break; } } return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); l->nr_items = 0; } #ifdef CONFIG_MEMCG_KMEM static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus, int begin, int end) { int i; for (i = begin; i < end; i++) kfree(memcg_lrus->lru[i]); } static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus, int begin, int end) { int i; for (i = begin; i < end; i++) { struct list_lru_one *l; l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL); if (!l) goto fail; init_one_lru(l); memcg_lrus->lru[i] = l; } return 0; fail: __memcg_destroy_list_lru_node(memcg_lrus, begin, i); return -ENOMEM; } static int memcg_init_list_lru_node(struct list_lru_node *nlru) { struct list_lru_memcg *memcg_lrus; int size = memcg_nr_cache_ids; memcg_lrus = kvmalloc(sizeof(*memcg_lrus) + size * sizeof(void *), GFP_KERNEL); if (!memcg_lrus) return -ENOMEM; if (__memcg_init_list_lru_node(memcg_lrus, 0, size)) { kvfree(memcg_lrus); return -ENOMEM; } RCU_INIT_POINTER(nlru->memcg_lrus, memcg_lrus); return 0; } static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) { struct list_lru_memcg *memcg_lrus; /* * This is called when shrinker has already been unregistered, * and nobody can use it. So, there is no need to use kvfree_rcu_local(). */ memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true); __memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids); kvfree(memcg_lrus); } static void kvfree_rcu_local(struct rcu_head *head) { struct list_lru_memcg *mlru; mlru = container_of(head, struct list_lru_memcg, rcu); kvfree(mlru); } static int memcg_update_list_lru_node(struct list_lru_node *nlru, int old_size, int new_size) { struct list_lru_memcg *old, *new; BUG_ON(old_size > new_size); old = rcu_dereference_protected(nlru->memcg_lrus, lockdep_is_held(&list_lrus_mutex)); new = kvmalloc(sizeof(*new) + new_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; if (__memcg_init_list_lru_node(new, old_size, new_size)) { kvfree(new); return -ENOMEM; } memcpy(&new->lru, &old->lru, old_size * sizeof(void *)); /* * The locking below allows readers that hold nlru->lock avoid taking * rcu_read_lock (see list_lru_from_memcg_idx). * * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); rcu_assign_pointer(nlru->memcg_lrus, new); spin_unlock_irq(&nlru->lock); call_rcu(&old->rcu, kvfree_rcu_local); return 0; } static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru, int old_size, int new_size) { struct list_lru_memcg *memcg_lrus; memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, lockdep_is_held(&list_lrus_mutex)); /* do not bother shrinking the array back to the old size, because we * cannot handle allocation failures here */ __memcg_destroy_list_lru_node(memcg_lrus, old_size, new_size); } static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { int i; lru->memcg_aware = memcg_aware; if (!memcg_aware) return 0; for_each_node(i) { if (memcg_init_list_lru_node(&lru->node[i])) goto fail; } return 0; fail: for (i = i - 1; i >= 0; i--) { if (!lru->node[i].memcg_lrus) continue; memcg_destroy_list_lru_node(&lru->node[i]); } return -ENOMEM; } static void memcg_destroy_list_lru(struct list_lru *lru) { int i; if (!list_lru_memcg_aware(lru)) return; for_each_node(i) memcg_destroy_list_lru_node(&lru->node[i]); } static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_size) { int i; if (!list_lru_memcg_aware(lru)) return 0; for_each_node(i) { if (memcg_update_list_lru_node(&lru->node[i], old_size, new_size)) goto fail; } return 0; fail: for (i = i - 1; i >= 0; i--) { if (!lru->node[i].memcg_lrus) continue; memcg_cancel_update_list_lru_node(&lru->node[i], old_size, new_size); } return -ENOMEM; } static void memcg_cancel_update_list_lru(struct list_lru *lru, int old_size, int new_size) { int i; if (!list_lru_memcg_aware(lru)) return; for_each_node(i) memcg_cancel_update_list_lru_node(&lru->node[i], old_size, new_size); } int memcg_update_all_list_lrus(int new_size) { int ret = 0; struct list_lru *lru; int old_size = memcg_nr_cache_ids; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &list_lrus, list) { ret = memcg_update_list_lru(lru, old_size, new_size); if (ret) goto fail; } out: mutex_unlock(&list_lrus_mutex); return ret; fail: list_for_each_entry_continue_reverse(lru, &list_lrus, list) memcg_cancel_update_list_lru(lru, old_size, new_size); goto out; } static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, int src_idx, struct mem_cgroup *dst_memcg) { struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ spin_lock_irq(&nlru->lock); src = list_lru_from_memcg_idx(nlru, src_idx); dst = list_lru_from_memcg_idx(nlru, dst_idx); list_splice_init(&src->list, &dst->list); if (src->nr_items) { dst->nr_items += src->nr_items; memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); src->nr_items = 0; } spin_unlock_irq(&nlru->lock); } static void memcg_drain_list_lru(struct list_lru *lru, int src_idx, struct mem_cgroup *dst_memcg) { int i; if (!list_lru_memcg_aware(lru)) return; for_each_node(i) memcg_drain_list_lru_node(lru, i, src_idx, dst_memcg); } void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg) { struct list_lru *lru; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &list_lrus, list) memcg_drain_list_lru(lru, src_idx, dst_memcg); mutex_unlock(&list_lrus_mutex); } #else static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { return 0; } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG_KMEM */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker) { int i; int err = -ENOMEM; #ifdef CONFIG_MEMCG_KMEM if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; #endif memcg_get_cache_ids(); lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) goto out; for_each_node(i) { spin_lock_init(&lru->node[i].lock); if (key) lockdep_set_class(&lru->node[i].lock, key); init_one_lru(&lru->node[i].lru); } err = memcg_init_list_lru(lru, memcg_aware); if (err) { kfree(lru->node); /* Do this so a list_lru_destroy() doesn't crash: */ lru->node = NULL; goto out; } list_lru_register(lru); out: memcg_put_cache_ids(); return err; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; memcg_get_cache_ids(); list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG_KMEM lru->shrinker_id = -1; #endif memcg_put_cache_ids(); } EXPORT_SYMBOL_GPL(list_lru_destroy);
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 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 // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; static unsigned int mp_hash_shift __read_mostly; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); static struct hlist_head *mount_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (mnt->mnt_sb->s_readonly_remount) return 1; /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * __mnt_want_write - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, __mnt_drop_write() must be * called. This is effectively a refcount. */ int __mnt_want_write(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until * MNT_WRITE_HOLD is cleared. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = __mnt_want_write(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_clone_write - get write access to a mount * @mnt: the mount on which to take a write * * This is effectively like mnt_want_write, except * it must only be used to take an extra write reference * on a mountpoint that we already know has a write reference * on it. This allows some optimisation. * * After finished, mnt_drop_write must be called as usual to * drop the reference. */ int mnt_clone_write(struct vfsmount *mnt) { /* superblock may be r/o */ if (__mnt_is_readonly(mnt)) return -EROFS; preempt_disable(); mnt_inc_writers(real_mount(mnt)); preempt_enable(); return 0; } EXPORT_SYMBOL_GPL(mnt_clone_write); /** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like __mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int __mnt_want_write_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) return __mnt_want_write(file->f_path.mnt); else return mnt_clone_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = __mnt_want_write_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * __mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * __mnt_want_write() call above. */ void __mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { __mnt_drop_write(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { __mnt_drop_write_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); static int mnt_make_readonly(struct mount *mnt) { int ret = 0; lock_mount_hash(); mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) ret = -EBUSY; else mnt->mnt.mnt_flags |= MNT_READONLY; /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; unlock_mount_hash(); return ret; } static int __mnt_unmake_readonly(struct mount *mnt) { lock_mount_hash(); mnt->mnt.mnt_flags &= ~MNT_READONLY; unlock_mount_hash(); return 0; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; smp_mb(); if (mnt_get_writers(mnt) > 0) { err = -EBUSY; break; } } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) { sb->s_readonly_remount = 1; smp_wmb(); } list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } lock_mount_hash(); if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /* * find the first mount at @dentry on vfsmount @mnt. * call under rcu_read_lock() */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } static inline void lock_ns_list(struct mnt_namespace *ns) { spin_lock(&ns->ns_lock); } static inline void unlock_ns_list(struct mnt_namespace *ns) { spin_unlock(&ns->ns_lock); } static inline bool mnt_is_cursor(struct mount *mnt) { return mnt->mnt.mnt_flags & MNT_CURSOR; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; bool is_covered = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { if (mnt_is_cursor(mnt)) continue; is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } unlock_ns_list(ns); up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); __attach_mnt(mnt, parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; list_splice(&head, n->list.prev); n->mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ if (unlikely(m->mnt_expiry_mark)) m->mnt_expiry_mark = 0; mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* path_is_mountpoint() - Check if path is a mount in the current * namespace. * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } #ifdef CONFIG_PROC_FS static struct mount *mnt_list_next(struct mnt_namespace *ns, struct list_head *p) { struct mount *mnt, *ret = NULL; lock_ns_list(ns); list_for_each_continue(p, &ns->list) { mnt = list_entry(p, typeof(*mnt), mnt_list); if (!mnt_is_cursor(mnt)) { ret = mnt; break; } } unlock_ns_list(ns); return ret; } /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; struct list_head *prev; down_read(&namespace_sem); if (!*pos) { prev = &p->ns->list; } else { prev = &p->cursor.mnt_list; /* Read after we'd reached the end? */ if (list_empty(prev)) return NULL; } return mnt_list_next(p->ns, prev); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_mounts *p = m->private; struct mount *mnt = v; ++*pos; return mnt_list_next(p->ns, &mnt->mnt_list); } static void m_stop(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *mnt = v; lock_ns_list(p->ns); if (mnt) list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list); else list_del_init(&p->cursor.mnt_list); unlock_ns_list(p->ns); up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor) { down_read(&namespace_sem); lock_ns_list(ns); list_del(&cursor->mnt_list); unlock_ns_list(ns); up_read(&namespace_sem); } #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @mnt: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } #ifdef CONFIG_MANDATORY_FILE_LOCKING static bool may_mandlock(void) { pr_warn_once("======================================================\n" "WARNING: the mand mount option is being deprecated and\n" " will be removed in v5.15!\n" "======================================================\n"); return capable(CAP_SYS_ADMIN); } #else static inline bool may_mandlock(void) { pr_warn("VFS: \"mand\" mount option not supported"); return false; } #endif static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { struct mount *res, *p, *q, *r, *parent; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { if (s->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ q = ERR_PTR(-EPERM); goto out; } else { s = skip_mnt_tree(s); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; parent = q; q = clone_mnt(p, p->mnt.mnt_root, flag); if (IS_ERR(q)) goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } static bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * * This creates a new vfsmount, which will be the clone of @path. The new will * not be attached anywhere in the namespace and will be private (i.e. changes * to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0, old, pending, sum; struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; old = ns->mounts; pending = ns->pending_mounts; sum = old + pending; if ((old > sum) || (pending > sum) || (max < sum) || (mounts > (max - sum))) return -ENOSPC; ns->pending_mounts = pending + mounts; return 0; } /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached * @parent_nd : if non-null, detach the source_mnt from its parent and * store the parent mount and mountpoint dentry. * (done when source_mnt is moved) * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *dest_mnt, struct mountpoint *dest_mp, bool moving) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; /* Preallocate a mountpoint in case the new mounts need * to be tucked under other mounts. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); lock_mount_hash(); if (err) goto out_cleanup_ids; for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } else { lock_mount_hash(); } if (moving) { unhash_mnt(source_mnt); attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } static struct mountpoint *lock_mount(struct path *path) { struct vfsmount *mnt; struct dentry *dentry = path->dentry; retry: inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); return ERR_PTR(-ENOENT); } namespace_lock(); mnt = lookup_mnt(path); if (likely(!mnt)) { struct mountpoint *mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); return mp; } return mp; } namespace_unlock(); inode_unlock(path->dentry->d_inode); path_put(path); path->mnt = mnt; dentry = path->dentry = dget(mnt->mnt_root); goto retry; } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, false); } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (path->dentry != path->mnt->mnt_root) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt_ns = ns; ns->mounts++; } ns->root = mnt; list_add_tail(&ns->list, &mnt->mnt_list); mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); return __mnt_unmake_readonly(mnt); } /* * Update the user-settable attributes on a mount. The caller must hold * sb->s_umount for writing. */ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); unlock_mount_hash(); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf = (char *)__get_free_page(GFP_KERNEL); char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM); struct tm tm; time64_to_tm(sb->s_time_max, 0, &tm); pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, tm.tm_year+1900, (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != mnt->mnt.mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; down_write(&sb->s_umount); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); up_write(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) set_mount_attributes(mnt, mnt_flags); } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_move_mount(struct path *old_path, struct path *new_path) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; mp = lock_mount(new_path); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (old_path->dentry != old_path->mnt->mnt_root) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, attached); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path->mnt->mnt_root == path->dentry) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, dentry))) { rcu_read_unlock(); err = 0; goto discard_locked; } rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if ((flags & SB_MANDLOCK) && !may_mandlock()) return -EPERM; /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kfree(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); atomic_set(&new_ns->count, 1); INIT_LIST_HEAD(&new_ns->list); init_waitqueue_head(&new_ns->poll); spin_lock_init(&new_ns->ns_lock); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; list_add_tail(&new_ns->list, &new->mnt_list); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { q->mnt_ns = new_ns; new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(p, old); } namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } mnt->mnt_ns = ns; ns->root = mnt; ns->mounts++; list_add(&mnt->mnt_list, &ns->list); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~(MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME)) return -EINVAL; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; ret = -EPERM; if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock()) goto err_unlock; newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); mnt->mnt_ns = ns; ns->root = mnt; ns->mounts = 1; list_add(&mnt->mnt_list, &ns->list); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; ret = do_move_mount(&from_path, &to_path); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (root.mnt->mnt_root != root.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (new.mnt->mnt_root != new.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); m->mnt_ns = ns; ns->root = m; ns->mounts = 1; list_add(&m->mnt_list, &ns->list); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!atomic_dec_and_test(&ns->count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { real_mount(mnt)->mnt_ns = NULL; synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) if (mnt[i]) real_mount(mnt[i])->mnt_ns = NULL; synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = &current->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { struct mount *child; int mnt_flags; if (mnt_is_cursor(mnt)) continue; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: unlock_ns_list(ns); up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, };
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 // SPDX-License-Identifier: GPL-2.0 /* * Functions related to segment and merge handling */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/scatterlist.h> #include <trace/events/block.h> #include "blk.h" #include "blk-rq-qos.h" static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) { struct bio_vec pb, nb; if (!bio_has_data(prev) || !queue_virt_boundary(q)) return false; /* * Don't merge if the 1st bio starts with non-zero offset, otherwise it * is quite difficult to respect the sg gap limit. We work hard to * merge a huge number of small single bios in case of mkfs. */ if (prev_rq) bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); if (pb.bv_offset & queue_virt_boundary(q)) return true; /* * We don't need to worry about the situation that the merged segment * ends in unaligned virt boundary: * * - if 'pb' ends aligned, the merged segment ends aligned * - if 'pb' ends unaligned, the next bio must include * one single bvec of 'nb', otherwise the 'nb' can't * merge with 'pb' */ bio_get_last_bvec(prev, &pb); bio_get_first_bvec(next, &nb); if (biovec_phys_mergeable(q, &pb, &nb)) return false; return __bvec_gap_to_prev(q, &pb, nb.bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, req, req->biotail, bio); } static inline bool req_gap_front_merge(struct request *req, struct bio *bio) { return bio_will_gap(req->q, NULL, bio, req->bio); } static struct bio *blk_bio_discard_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { unsigned int max_discard_sectors, granularity; int alignment; sector_t tmp; unsigned split_sectors; *nsegs = 1; /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); max_discard_sectors = min(q->limits.max_discard_sectors, bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { /* XXX: warn */ return NULL; } if (bio_sectors(bio) <= max_discard_sectors) return NULL; split_sectors = max_discard_sectors; /* * If the next starting sector would be misaligned, stop the discard at * the previous aligned sector. */ alignment = (q->limits.discard_alignment >> 9) % granularity; tmp = bio->bi_iter.bi_sector + split_sectors - alignment; tmp = sector_div(tmp, granularity); if (split_sectors > tmp) split_sectors -= tmp; return bio_split(bio, split_sectors, GFP_NOIO, bs); } static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { *nsegs = 0; if (!q->limits.max_write_zeroes_sectors) return NULL; if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors) return NULL; return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs); } static struct bio *blk_bio_write_same_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *nsegs) { *nsegs = 1; if (!q->limits.max_write_same_sectors) return NULL; if (bio_sectors(bio) <= q->limits.max_write_same_sectors) return NULL; return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } /* * Return the maximum number of sectors from the start of a bio that may be * submitted as a single request to a block device. If enough sectors remain, * align the end to the physical block size. Otherwise align the end to the * logical block size. This approach minimizes the number of non-aligned * requests that are submitted to a block device if the start of a bio is not * aligned to a physical block boundary. */ static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); unsigned max_sectors = sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1); max_sectors += start_offset; max_sectors &= ~(pbs - 1); if (max_sectors > start_offset) return max_sectors - start_offset; return sectors & ~(lbs - 1); } static inline unsigned get_max_segment_size(const struct request_queue *q, struct page *start_page, unsigned long offset) { unsigned long mask = queue_segment_boundary(q); offset = mask & (page_to_phys(start_page) + offset); /* * overflow may be triggered in case of zero page physical address * on 32bit arch, use queue's max segment size when that happens. */ return min_not_zero(mask - offset + 1, (unsigned long)queue_max_segment_size(q)); } /** * bvec_split_segs - verify whether or not a bvec should be split in the middle * @q: [in] request queue associated with the bio associated with @bv * @bv: [in] bvec to examine * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that * bio without exceeding @max_segs * @sectors: [in,out] Number of sectors in the bio being built. Incremented * by the number of sectors from @bv that may be appended to that * bio without exceeding @max_sectors * @max_segs: [in] upper bound for *@nsegs * @max_sectors: [in] upper bound for *@sectors * * When splitting a bio, it can happen that a bvec is encountered that is too * big to fit in a single segment and hence that it has to be split in the * middle. This function verifies whether or not that should happen. The value * %true is returned if and only if appending the entire @bv to a bio with * *@nsegs segments and *@sectors sectors would make that bio unacceptable for * the block driver. */ static bool bvec_split_segs(const struct request_queue *q, const struct bio_vec *bv, unsigned *nsegs, unsigned *sectors, unsigned max_segs, unsigned max_sectors) { unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9; unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; unsigned seg_size = 0; while (len && *nsegs < max_segs) { seg_size = get_max_segment_size(q, bv->bv_page, bv->bv_offset + total_len); seg_size = min(seg_size, len); (*nsegs)++; total_len += seg_size; len -= seg_size; if ((bv->bv_offset + total_len) & queue_virt_boundary(q)) break; } *sectors += total_len >> 9; /* tell the caller to split the bvec if it is too big to fit */ return len > 0 || bv->bv_len > max_len; } /** * blk_bio_segment_split - split a bio in two bios * @q: [in] request queue pointer * @bio: [in] bio to be split * @bs: [in] bio set to allocate the clone from * @segs: [out] number of segments in the bio with the first half of the sectors * * Clone @bio, update the bi_iter of the clone to represent the first sectors * of @bio and update @bio->bi_iter to represent the remaining sectors. The * following is guaranteed for the cloned bio: * - That it has at most get_max_io_size(@q, @bio) sectors. * - That it has at most queue_max_segments(@q) segments. * * Except for discard requests the cloned bio will point at the bi_io_vec of * the original bio. It is the responsibility of the caller to ensure that the * original bio is not freed before the cloned bio. The caller is also * responsible for ensuring that @bs is only destroyed after processing of the * split bio has finished. */ static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, unsigned *segs) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; unsigned nsegs = 0, sectors = 0; const unsigned max_sectors = get_max_io_size(q, bio); const unsigned max_segs = queue_max_segments(q); bio_for_each_bvec(bv, bio, iter) { /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; if (nsegs < max_segs && sectors + (bv.bv_len >> 9) <= max_sectors && bv.bv_offset + bv.bv_len <= PAGE_SIZE) { nsegs++; sectors += bv.bv_len >> 9; } else if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs, max_sectors)) { goto split; } bvprv = bv; bvprvp = &bvprv; } *segs = nsegs; return NULL; split: *segs = nsegs; return bio_split(bio, sectors, GFP_NOIO, bs); } /** * __blk_queue_split - split a bio and submit the second half * @bio: [in, out] bio to be split * @nr_segs: [out] number of segments in the first bio * * Split a bio into two bios, chain the two bios, submit the second half and * store a pointer to the first half in *@bio. If the second bio is still too * big it will be split by a recursive call to this function. Since this * function may allocate a new bio from @bio->bi_disk->queue->bio_split, it is * the responsibility of the caller to ensure that * @bio->bi_disk->queue->bio_split is only released after processing of the * split bio has finished. */ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs) { struct request_queue *q = (*bio)->bi_disk->queue; struct bio *split = NULL; switch (bio_op(*bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs); break; case REQ_OP_WRITE_ZEROES: split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, nr_segs); break; case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, &q->bio_split, nr_segs); break; default: /* * All drivers must accept single-segments bios that are <= * PAGE_SIZE. This is a quick and dirty check that relies on * the fact that bi_io_vec[0] is always valid if a bio has data. * The check might lead to occasional false negatives when bios * are cloned, but compared to the performance impact of cloned * bios themselves the loop below doesn't matter anyway. */ if (!q->limits.chunk_sectors && (*bio)->bi_vcnt == 1 && ((*bio)->bi_io_vec[0].bv_len + (*bio)->bi_io_vec[0].bv_offset) <= PAGE_SIZE) { *nr_segs = 1; break; } split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs); break; } if (split) { /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); submit_bio_noacct(*bio); *bio = split; blk_throtl_charge_bio_split(*bio); } } /** * blk_queue_split - split a bio and submit the second half * @bio: [in, out] bio to be split * * Split a bio into two bios, chains the two bios, submit the second half and * store a pointer to the first half in *@bio. Since this function may allocate * a new bio from @bio->bi_disk->queue->bio_split, it is the responsibility of * the caller to ensure that @bio->bi_disk->queue->bio_split is only released * after processing of the split bio has finished. */ void blk_queue_split(struct bio **bio) { unsigned int nr_segs; __blk_queue_split(bio, &nr_segs); } EXPORT_SYMBOL(blk_queue_split); unsigned int blk_recalc_rq_segments(struct request *rq) { unsigned int nr_phys_segs = 0; unsigned int nr_sectors = 0; struct req_iterator iter; struct bio_vec bv; if (!rq->bio) return 0; switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: if (queue_max_discard_segments(rq->q) > 1) { struct bio *bio = rq->bio; for_each_bio(bio) nr_phys_segs++; return nr_phys_segs; } return 1; case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: return 1; } rq_for_each_bvec(bv, rq, iter) bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors, UINT_MAX, UINT_MAX); return nr_phys_segs; } static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) { if (!*sg) return sglist; /* * If the driver previously mapped a shorter list, we could see a * termination bit prematurely unless it fully inits the sg table * on each mapping. We KNOW that there must be more entries here * or the driver would be buggy, so force clear the termination bit * to avoid doing a full sg_init_table() in drivers for each command. */ sg_unmark_end(*sg); return sg_next(*sg); } static unsigned blk_bvec_map_sg(struct request_queue *q, struct bio_vec *bvec, struct scatterlist *sglist, struct scatterlist **sg) { unsigned nbytes = bvec->bv_len; unsigned nsegs = 0, total = 0; while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; unsigned len = min(get_max_segment_size(q, bvec->bv_page, offset), nbytes); struct page *page = bvec->bv_page; /* * Unfortunately a fair number of drivers barf on scatterlists * that have an offset larger than PAGE_SIZE, despite other * subsystems dealing with that invariant just fine. For now * stick to the legacy format where we never present those from * the block layer, but the code below should be removed once * these offenders (mostly MMC/SD drivers) are fixed. */ page += (offset >> PAGE_SHIFT); offset &= ~PAGE_MASK; *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, page, len, offset); total += len; nbytes -= len; nsegs++; } return nsegs; } static inline int __blk_bvec_map_sg(struct bio_vec bv, struct scatterlist *sglist, struct scatterlist **sg) { *sg = blk_next_sg(sg, sglist); sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset); return 1; } /* only try to merge bvecs into one sg if they are from two bios */ static inline bool __blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec, struct bio_vec *bvprv, struct scatterlist **sg) { int nbytes = bvec->bv_len; if (!*sg) return false; if ((*sg)->length + nbytes > queue_max_segment_size(q)) return false; if (!biovec_phys_mergeable(q, bvprv, bvec)) return false; (*sg)->length += nbytes; return true; } static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; int nsegs = 0; bool new_bio = false; for_each_bio(bio) { bio_for_each_bvec(bvec, bio, iter) { /* * Only try to merge bvecs from two bios given we * have done bio internal merge when adding pages * to bio */ if (new_bio && __blk_segment_map_sg_merge(q, &bvec, &bvprv, sg)) goto next_bvec; if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE) nsegs += __blk_bvec_map_sg(bvec, sglist, sg); else nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg); next_bvec: new_bio = false; } if (likely(bio->bi_iter.bi_size)) { bvprv = bvec; new_bio = true; } } return nsegs; } /* * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist, struct scatterlist **last_sg) { int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, last_sg); else if (rq->bio) nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); if (*last_sg) sg_mark_end(*last_sg); /* * Something must have been wrong if the figured number of * segment is bigger than number of req's physical segments */ WARN_ON(nsegs > blk_rq_nr_phys_segments(rq)); return nsegs; } EXPORT_SYMBOL(__blk_rq_map_sg); static inline unsigned int blk_rq_get_max_segments(struct request *rq) { if (req_op(rq) == REQ_OP_DISCARD) return queue_max_discard_segments(rq->q); return queue_max_segments(rq->q); } static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; /* discard request merge won't add new segment */ if (req_op(req) == REQ_OP_DISCARD) return 1; if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* * This will form the start of a new hw segment. Bump both * counters. */ req->nr_phys_segments += nr_phys_segs; return 1; no_merge: req_set_nomerge(req->q, req); return 0; } int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_back_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_back_merge(req, bio)) return 0; if (!bio_crypt_ctx_back_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_front_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_front_merge(req, bio)) return 0; if (!bio_crypt_ctx_front_mergeable(req, bio)) return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) { req_set_nomerge(req->q, req); return 0; } return ll_new_hw_segment(req, bio, nr_segs); } static bool req_attempt_discard_merge(struct request_queue *q, struct request *req, struct request *next) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(next->bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next); return true; no_merge: req_set_nomerge(q, req); return false; } static int ll_merge_requests_fn(struct request_queue *q, struct request *req, struct request *next) { int total_phys_segments; if (req_gap_back_merge(req, next->bio)) return 0; /* * Will it become too large? */ if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) return 0; total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; if (total_phys_segments > blk_rq_get_max_segments(req)) return 0; if (blk_integrity_merge_rq(q, req, next) == false) return 0; if (!bio_crypt_ctx_merge_rq(req, next)) return 0; /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; } /** * blk_rq_set_mixed_merge - mark a request as mixed merge * @rq: request to mark as mixed merge * * Description: * @rq is about to be mixed merged. Make sure the attributes * which can be mixed are set in each bio and mark @rq as mixed * merged. */ void blk_rq_set_mixed_merge(struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; if (rq->rq_flags & RQF_MIXED_MERGE) return; /* * @rq will no longer represent mixable attributes for all the * contained bios. It will just track those of the first one. * Distributes the attributs to each bio. */ for (bio = rq->bio; bio; bio = bio->bi_next) { WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) && (bio->bi_opf & REQ_FAILFAST_MASK) != ff); bio->bi_opf |= ff; } rq->rq_flags |= RQF_MIXED_MERGE; } static void blk_account_io_merge_request(struct request *req) { if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); hd_struct_put(req->part); } } static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { if (blk_discard_mergable(req)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) return ELEVATOR_BACK_MERGE; return ELEVATOR_NO_MERGE; } /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. */ static struct request *attempt_merge(struct request_queue *q, struct request *req, struct request *next) { if (!rq_mergeable(req) || !rq_mergeable(next)) return NULL; if (req_op(req) != req_op(next)) return NULL; if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk) return NULL; if (req_op(req) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(req->bio, next->bio)) return NULL; /* * Don't allow merge of different write hints, or for a hint with * non-hint IO. */ if (req->write_hint != next->write_hint) return NULL; if (req->ioprio != next->ioprio) return NULL; /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn * will have updated segment counts, update sector * counts here. Handle DISCARDs separately, as they * have separate settings. */ switch (blk_try_req_merge(req, next)) { case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; break; case ELEVATOR_BACK_MERGE: if (!ll_merge_requests_fn(q, req, next)) return NULL; break; default: return NULL; } /* * If failfast settings disagree or any of the two is already * a mixed merge, mark both as mixed before proceeding. This * makes sure that all involved bios have mixable attributes * set properly. */ if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) || (req->cmd_flags & REQ_FAILFAST_MASK) != (next->cmd_flags & REQ_FAILFAST_MASK)) { blk_rq_set_mixed_merge(req); blk_rq_set_mixed_merge(next); } /* * At this point we have either done a back merge or front merge. We * need the smaller start_time_ns of the merged requests to be the * current request for accounting purposes. */ if (next->start_time_ns < req->start_time_ns) req->start_time_ns = next->start_time_ns; req->biotail->bi_next = next->bio; req->biotail = next->biotail; req->__data_len += blk_rq_bytes(next); if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); /* * 'next' is going away, so update stats accordingly */ blk_account_io_merge_request(next); trace_block_rq_merge(q, next); /* * ownership of bio passed from next to req, return 'next' for * the caller to free */ next->bio = NULL; return next; } static struct request *attempt_back_merge(struct request_queue *q, struct request *rq) { struct request *next = elv_latter_request(q, rq); if (next) return attempt_merge(q, rq, next); return NULL; } static struct request *attempt_front_merge(struct request_queue *q, struct request *rq) { struct request *prev = elv_former_request(q, rq); if (prev) return attempt_merge(q, prev, rq); return NULL; } int blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next) { struct request *free; free = attempt_merge(q, rq, next); if (free) { blk_put_request(free); return 1; } return 0; } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) { if (!rq_mergeable(rq) || !bio_mergeable(bio)) return false; if (req_op(rq) != bio_op(bio)) return false; /* different data direction or already started, don't merge */ if (bio_data_dir(bio) != rq_data_dir(rq)) return false; /* must be same device */ if (rq->rq_disk != bio->bi_disk) return false; /* only merge integrity protected bio into ditto rq */ if (blk_integrity_merge_bio(rq->q, rq, bio) == false) return false; /* Only merge if the crypt contexts are compatible */ if (!bio_crypt_rq_ctx_compatible(rq, bio)) return false; /* must be using the same buffer */ if (req_op(rq) == REQ_OP_WRITE_SAME && !blk_write_same_mergeable(rq->bio, bio)) return false; /* * Don't allow merge of different write hints, or for a hint with * non-hint IO. */ if (rq->write_hint != bio->bi_write_hint) return false; if (rq->ioprio != bio_prio(bio)) return false; return true; } enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector) return ELEVATOR_FRONT_MERGE; return ELEVATOR_NO_MERGE; } static void blk_account_io_merge_bio(struct request *req) { if (!blk_do_io_stat(req)) return; part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); part_stat_unlock(); } enum bio_merge_status { BIO_MERGE_OK, BIO_MERGE_NONE, BIO_MERGE_FAILED, }; static enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_back_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_backmerge(req->q, req, bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; bio_crypt_free_ctx(bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_front_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_front_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; trace_block_bio_frontmerge(req->q, req, bio); rq_qos_merge(req->q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); bio->bi_next = req->bio; req->bio = bio; req->__sector = bio->bi_iter.bi_sector; req->__data_len += bio->bi_iter.bi_size; bio_crypt_do_front_merge(req, bio); blk_account_io_merge_bio(req); return BIO_MERGE_OK; } static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q, struct request *req, struct bio *bio) { unsigned short segments = blk_rq_nr_discard_segments(req); if (segments >= queue_max_discard_segments(q)) goto no_merge; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) goto no_merge; rq_qos_merge(q, req, bio); req->biotail->bi_next = bio; req->biotail = bio; req->__data_len += bio->bi_iter.bi_size; req->nr_phys_segments = segments + 1; blk_account_io_merge_bio(req); return BIO_MERGE_OK; no_merge: req_set_nomerge(q, req); return BIO_MERGE_FAILED; } static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q, struct request *rq, struct bio *bio, unsigned int nr_segs, bool sched_allow_merge) { if (!blk_rq_merge_ok(rq, bio)) return BIO_MERGE_NONE; switch (blk_try_merge(rq, bio)) { case ELEVATOR_BACK_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_back_merge(rq, bio, nr_segs); break; case ELEVATOR_FRONT_MERGE: if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) return bio_attempt_front_merge(rq, bio, nr_segs); break; case ELEVATOR_DISCARD_MERGE: return bio_attempt_discard_merge(q, rq, bio); default: return BIO_MERGE_NONE; } return BIO_MERGE_FAILED; } /** * blk_attempt_plug_merge - try to merge with %current's plugged list * @q: request_queue new bio is being queued at * @bio: new bio being queued * @nr_segs: number of segments in @bio * @same_queue_rq: pointer to &struct request that gets filled in when * another request associated with @q is found on the plug list * (optional, may be %NULL) * * Determine whether @bio being queued on @q can be merged with a request * on %current's plugged list. Returns %true if merge was successful, * otherwise %false. * * Plugging coalesces IOs from the same issuer for the same purpose without * going through @q->queue_lock. As such it's more of an issuing mechanism * than scheduling, and the request, while may have elvpriv data, is not * added on the elevator at this point. In addition, we don't have * reliable access to the elevator outside queue lock. Only check basic * merging parameters without querying the elevator. * * Caller must ensure !blk_queue_nomerges(q) beforehand. */ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **same_queue_rq) { struct blk_plug *plug; struct request *rq; struct list_head *plug_list; plug = blk_mq_plug(q, bio); if (!plug) return false; plug_list = &plug->mq_list; list_for_each_entry_reverse(rq, plug_list, queuelist) { if (rq->q == q && same_queue_rq) { /* * Only blk-mq multiple hardware queues case checks the * rq in the same queue, there should be only one such * rq in a queue **/ *same_queue_rq = rq; } if (rq->q != q) continue; if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK) return true; } return false; } /* * Iterate list of requests and see if we can merge this bio with any * of them. */ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs) { struct request *rq; int checked = 8; list_for_each_entry_reverse(rq, list, queuelist) { if (!checked--) break; switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) { case BIO_MERGE_NONE: continue; case BIO_MERGE_OK: return true; case BIO_MERGE_FAILED: return false; } } return false; } EXPORT_SYMBOL_GPL(blk_bio_list_merge); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request) { struct request *rq; switch (elv_merge(q, &rq, bio)) { case ELEVATOR_BACK_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_back_merge(q, rq); if (!*merged_request) elv_merged_request(q, rq, ELEVATOR_BACK_MERGE); return true; case ELEVATOR_FRONT_MERGE: if (!blk_mq_sched_allow_merge(q, rq, bio)) return false; if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK) return false; *merged_request = attempt_front_merge(q, rq); if